41st week of 2019 patent applcation highlights part 42 |
Patent application number | Title | Published |
20190311171 | FINGERPRINT SENSING PANEL AND FINGERPRINT SENSOR THEREOF - A fingerprint sensing panel and a fingerprint sensor thereof are provided. The fingerprint sensor includes first to third switches, a first capacitor, an impedance variation element and a sensing circuit. The first switch receives a system high voltage and is controlled by a pre-charge signal. The first capacitor is coupled between the first switch and a reference voltage. The impedance variation element is coupled between the first switch and the reference voltage, and an impedance value of the impedance variation element is changed according to a vertical distance between the impedance variation element and a skin surface. The second switch receives the system high voltage. The third switch receives a read signal. The sensing circuit is coupled to the third switch and provides a fingerprint determination voltage. | 2019-10-10 |
20190311172 | ELECTRONIC DEVICE COMPRISING SENSOR AND METHOD FOR OPERATING SAME - Disclosed is an electronic device including a housing including a transparent cover including a first region and a second region adjacent to the first region, a touchscreen display interposed between the first region and a second surface of the housing and exposed through the first region, an opaque layer interposed between the second region of the transparent cover and the second surface and exposed through the second region, a fingerprint sensor interposed between the opaque layer and the second surface, and a pressure sensor interposed between the fingerprint sensor and the second surface and sensing a pressure of an external object against the opaque layer. The pressure sensor includes a first electrode substantially in parallel with the opaque layer, a second electrode spaced from the first electrode layer and extending substantially in parallel in the second direction, and a dielectric layer interposed between the first electrode and the second electrode. | 2019-10-10 |
20190311173 | METHOD AND SYSTEM FOR BIOMETRIC SENSING AND SUBCUTANEOUS STRUCTURE DETECTION - A system, apparatus and method for obtaining biometric data from characteristics of a fingerprint and obtaining characteristics of subcutaneous structures that are embedded within finger tissue and located in relation to the fingerprint. | 2019-10-10 |
20190311174 | METHOD AND SYSTEM FOR 2D AND 3D BIOMETRIC SENSING USING A SAME SENSOR - A system, apparatus and method for obtaining biometric data from characteristics of a fingerprint and obtaining characteristics of subcutaneous structures that are embedded within finger tissue and located in relation to the fingerprint. | 2019-10-10 |
20190311175 | Fingerprint Collection Method and Terminal - A fingerprint collection method and a terminal, where the method includes obtaining, by a terminal, a fingerprint collection instruction, where the fingerprint collection instruction instructs to collect a fingerprint using a fingerprint sensor integrated on a function key, collecting, by the terminal using the fingerprint sensor based on the fingerprint collection instruction, fingerprint information recorded by a user on the function key, obtaining, by the terminal on the function key at any moment of collecting the fingerprint information, a first key event triggered by the user, where the first key event is any operation other than a fingerprint recording event, and discarding, by the terminal, the first key event. | 2019-10-10 |
20190311176 | UNDER-SCREEN FINGERPRINT READER - An optical fingerprint reader apparatus is configured to detect skin features of a finger using Frustrated Total Internal Reflection contrast detection. The apparatus comprises a display comprising a transparent cover and a substrate comprising an array of active pixels that serve as an illuminator of the apparatus. The apparatus comprises a pinhole array which can be affixed to a transparent display or integrated within an opaque display. An optical sensor is optically coupled to the display via the pinhole array and comprises an array of photosensors. A processor is coupled to the display and the optical sensor. The processor is configured to control reading of signals from the photosensors and to control illumination of selected active pixels in accordance with a predefined scanning pattern that covers a finger sensing region of the transparent cover during a fingerprint reading operation. | 2019-10-10 |
20190311177 | COMPLEX BIOMETRIC SENSOR INCLUDING COLOR CONVERSION LAYER - Provided is a complex biometric sensor. The complex biometric sensor includes a substrate including a light emitting region, a first light receiving region, and a second light receiving region, a light emitting part disposed adjacent to the substrate in the light emitting region, a color conversion layer disposed on the substrate in the light emitting region and vertically overlapping the light emitting part; a first light receiving layer disposed on the substrate in the first light receiving region, and a second light receiving layer disposed on the substrate in the second light receiving region. The light emitting part generates light of a first wavelength. The color conversion layer receives light of the first wavelength and emits the light of the first wavelength and light of the second wavelength. The first light receiving layer detects the light of the first wavelength. The second light receiving layer detects the light of the second wavelength. | 2019-10-10 |
20190311178 | METHODS AND DEVICES FOR READING MICROARRAYS - In one embodiment of the invention, a method to image a probe array is described that includes focusing on a plurality of fiducials on a surface of an array. The method utilizes obtaining the best z position of the fiducials and using a surface fitting algorithm to produce a surface fit profile. One or more surface non-flatness parameters can be adjusted to improve the flatness image of the array surface to be imaged. | 2019-10-10 |
20190311179 | SYSTEM AND METHOD FOR PROVIDING A REAL-TIME, ONLINE BIOMETRIC SIGNATURE - A system is provided for generating an online biometrically accurate electronic signature. The system includes a computer interface module which records movement of a cursor on a computer screen and outputs the recorded data. A signature generation module which receives the recorded data and generates a graphical image based upon the recorded data. | 2019-10-10 |
20190311180 | FACE SENSING MODULE AND COMPUTING DEVICE USING SAME - A face sensing module for a computing device includes a frame, a depth sensor, and an RGB camera. The frame includes first and second side portions and a cross portion. The depth sensor includes first and second infrared cameras, and an infrared light emitting unit. The first infrared camera is mounted on the first side portion. The second infrared camera is mounted on the second side portion. The infrared light emitting unit is mounted on the cross portion, with an infrared emitter and an infrared guide. Infrared light emitted is guided out. The RGB camera is mounted on the first side portion. The first and second infrared cameras and the RGB camera are optically aligned before being mounted together inside the housing of the computing device to ensure precise mountings and the durability of precise alignment notwithstanding handling by a user. | 2019-10-10 |
20190311181 | Face Tracking Method and Device - Disclosed is face tracking method and device. The method includes: acquiring an initial facial image in a to-be-tracked picture; performing binarization processing on the initial facial image according to a standard range of color parameter and an actual value of the color parameter of each pixel in the initial facial image, to obtain a binarized facial image; acquiring a position of a preset organ in the binarized facial image; and acquiring a position of a final facial image according to the position of the preset organ and a position of the initial facial image. | 2019-10-10 |
20190311182 | AUTOMATED AND UNSUPERVISED CURATION OF IMAGE DATASETS - Datasets containing a plurality of images are processed. A plurality of regions within the images are determined, where each of the plurality of regions corresponds to a facial region. A feature vector is generated for each of the plurality of pixel regions, and the plurality of pixel regions are clustered into a plurality of clusters based on the generated feature vectors. An initial score is assigned to each respective pixel region in the plurality of pixel regions, and the plurality of pixel regions are sorted based on the assigned scores. A representative index is computed for each respective pixel region by comparing each respective pixel regions with each other pixel region in the respective cluster. The score of each pixel region is modified based on the computed representative indices, and the pixel regions are sorted based on the modified scores. A confidence index is generated for the unified dataset. | 2019-10-10 |
20190311183 | FEATURE MATCHING WITH A SUBSPACE SPANNED BY MULTIPLE REPRESENTATIVE FEATURE VECTORS - Methods, systems, and devices for object recognition are described. A device may generate a subspace based at least in part on a set of representative feature vectors for an object. The device may obtain an array of pixels representing an image. The device may determine a probe feature vector for the image by applying a convolutional operation to the array of pixels. The device may create a reconstructed feature vector in the subspace based at least in part on the set of representative feature vectors and the probe feature vector. The device may compare the reconstructed feature vector and the probe feature vector and recognize the object in the image based at least in part on the comparison. For example, the described techniques may support pose invariant facial recognition or other such object recognition applications. | 2019-10-10 |
20190311184 | High Accuracy and Volume Facial Recognition on Mobile Platforms - Disclosed are systems and methods related to facial recognition. An image of a subject can be captured via a camera on a mobile device. The image can be classified according to a device type, whether the image is captured indoors or outdoors, and a standoff distance. Facial features can be extracted from the image based on the image category. The facial features can be compared with a predefined set of facial features in a database. An identification of the subject can be made in response to the comparison. | 2019-10-10 |
20190311185 | SYSTEM AND METHOD FOR MANUFACTURING AND INSPECTING IDENTIFICATION DOCUMENTS - A document authentication system is configured to support enhanced services with advanced security features within a document and by linking information embedded in the document with a secure infrastructure. | 2019-10-10 |
20190311186 | FACE RECOGNITION METHOD - A face recognition method is disclosed. First, an input image is received. After the input image is received, face recognition is performed on the input image by using a first CNN model to generate at least one first ROI, where each first ROI includes a suspicious image, and a proportion value of a pixel value of the suspicious image in a pixel value of the first ROI is greater than a proportion value of the pixel value of the suspicious image in a pixel value of the input image. Then, face recognition is performed on each first ROI by using a second CNN model to generate at least one second ROI, where the quantity of convolution operation layers of the second CNN model is less than the quantity of convolution operation layers of the first CNN model. Finally, a mark is displayed in the input image. | 2019-10-10 |
20190311187 | COMPUTERIZED SYSTEM AND METHOD FOR CONTINUOUSLY AUTHENTICATING A USER'S IDENTITY DURING AN ONLINE SESSION AND PROVIDING ONLINE FUNCTIONALITY BASED THEREFROM - A method and system is disclosed for confirming the identity of students taking an exam online. A camera or similar device compares the image of a student to a known and verified Reference Image to confirm the identity of the student. Using data analysis on answers during the exam coupled with both the uniqueness of the browser used and the location of taking the online exam, provides information on whether the student may have been obtaining help from others. The result is identifying students who are cheating, colluding, or conspiring to falsify test scores. | 2019-10-10 |
20190311188 | Face emotion recognition method based on dual-stream convolutional neural network - A face emotion recognition method based on dual-stream convolutional neural network uses a multi-scale face expression recognition network to single frame face images and face sequences to perform learning classification. The method includes constructing a multi-scale face expression recognition network which includes a channel network with a resolution of 224×224 and a channel network with a resolution of 336×336, extracting facial expression characteristics at different resolutions through the recognition network, effectively combining static characteristics of images and dynamic characteristics of expression sequence to perform training and learning, fusing the two channel models, testing and obtaining a classification effect of facial expressions. The present invention fully utilizes the advantages of deep learning, effectively avoids the problems of manual extraction of feature deviations and long time, and makes the method provided by the present invention more adaptable. Moreover, the present invention improves the accuracy and productivity of expression recognition. | 2019-10-10 |
20190311189 | PHOTOGRAPHIC EMOJI COMMUNICATIONS SYSTEMS AND METHODS OF USE - Photographic emoji communications systems and methods of use are provided herein. An example method receiving a plurality of image files from a user device, each of the image files including a selfie of the user; for each of the plurality of image files, determining a reaction emotion of an associated selfie based on facial attributes of the user; storing the plurality of image files in a repository, each of the plurality of image files being labeled with a respective reaction emotion as a selfiemoji; receiving a request to include one of the selfiemojis in a message; and inserting one of the selfiemojis into the message. | 2019-10-10 |
20190311190 | METHODS AND APPARATUSES FOR DETERMINING HAND THREE-DIMENSIONAL DATA - A method for determining hand three-dimensional data includes: obtaining a first hand image and a second hand image captured by a binocular photographing system; identifying, from each of the first hand image and the second hand image, at least one key point and a region profile covering the at least one key point; determining depth information of the at least one key point and depth information of the region profile according to a photographing parameter of the binocular photographing system, the at least one key point and the region profile identified from the first hand image, and the at least one key point and the region profile identified from the second hand image; and determining hand three-dimensional data according to the at least one key point and the depth information of the at least one key point together with the region profile and the depth information of the region profile. | 2019-10-10 |
20190311191 | HIERARCHICAL DIFFERENTIAL IMAGE FILTERS FOR SKIN ANALYSIS - There is provided a framework including systems and methods for analyzing skin parameters from images or videos showing skin. Using a series of Hierarchical Differential Image Filters (HDIF), it becomes possible to detect different skin features such as wrinkles, spots, and roughness. The hierarchical differential image filter computes two enhancements to an image showing skin at two different levels of enhancement, determines a differential image using the two enhancements and computes the skin analysis rating using the differential image. These skin ratings are comparably accurate to actual ratings by dermatologists. | 2019-10-10 |
20190311192 | VIDEO MONITORING - One example of a video monitoring system includes a frame acquisition subsystem, a stage gate motion detection subsystem, a person detection subsystem, a face recognition subsystem, and an alert emission subsystem. The frame acquisition subsystem extracts frames from an input video. The stage gate motion detection subsystem separates background motion from foreground motion within frames. The person detection subsystem detects people including faces and bodies within the foreground motion. The face recognition subsystem matches detected faces to previously registered users. The alert emission subsystem provides alerts based on events detected by the stage gate motion subsystem, the person detection subsystem, and the face recognition subsystem. | 2019-10-10 |
20190311193 | METHODS AND SYSTEMS FOR DATA RETRIEVAL FROM AN IMAGE - Various embodiments illustrated herein disclose a method that includes receiving a plurality of images from an image capturing unit. Thereafter, an image evaluation process is executed on each of plurality of sections in each of the plurality of images. The image evaluation process includes performing optical character recognition (OCR) on each of the plurality of sections in each of the plurality of images to generate text corresponding to the plurality of respective sections. Further, the image evaluation process includes querying a linguistic database to identify one or more errors in the generated text. Further, the method includes modifying one or more image characteristics of each of the plurality of images and repeating the execution of the image evaluation process on the modified plurality of images until at least the calculated statistical score is less than a pre-defined statistical score threshold. | 2019-10-10 |
20190311194 | CHARACTER RECOGNITION USING HIERARCHICAL CLASSIFICATION - Aspects of the disclosure provide for mechanisms for character recognition using neural networks. A method of the disclosure includes assigning, using a first-level classifier of a grapheme classifier, an input grapheme image to a first grapheme cluster of a plurality of grapheme clusters, wherein the first grapheme cluster comprises a first plurality of graphemes; selecting, by a processing device, a classifier from a plurality of second-level classifiers of the grapheme classifier based on the first grapheme cluster, wherein the selected classifier is trained to recognize the first plurality of graphemes; and processing the input grapheme image using the selected classifier to recognize at least one character in the input grapheme image. | 2019-10-10 |
20190311195 | INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING SYSTEM, AND NON-TRANSITORY COMPUTER READABLE MEDIUM STORING PROGRAM - An information processing apparatus includes a first acquisition section that acquires an image of a digitized document, a second acquisition section that acquires date information from the image acquired by the first acquisition section, a third acquisition section that acquires an application period different from an application period in a case where a recipient receiving the document is the same as an operator who has performed an operation of digitizing the document, in a case where the recipient is different from the operator, and a processing section that performs processing of preserving the image in a case where a current date and time satisfies a preset criterion for an application deadline set based on the date information acquired by the second acquisition section and the application period acquired by the third acquisition section. | 2019-10-10 |
20190311196 | Proportional Markers on a Map - The systems may include dividing a digital map provided by a mapping system into a matrix having a plurality of cells; assigning a cell of the plurality of cells to encompass a geographic region of the digital map; calculating a number of sites of interest in the cell; creating a marker comprising a first count number representing the number of sites of interest in the cell; and sharing the marker with a browser for display on the digital map. | 2019-10-10 |
20190311197 | AUGMENTED REALITY FOR PLANT STAND MANAGEMENT - A plant stand management system includes a sensor unit configured to capture images of a plant stand, an applicator, and a controller communicatively coupled to the sensor unit and the applicator. The controller is configured to receive the captured images, process the captured images for determining one or more characteristics of the plant stand, generate one or more control signals based on the one or more characteristics, and send the one or more control signals to the applicator. The applicator is configured to perform at least one action on the plant stand based on the one or more control signals. | 2019-10-10 |
20190311198 | AUGMENTED REALITY FOR PLANT STAND MANAGEMENT - A plant stand management system includes a sensor unit configured to capture images of a plant stand, an applicator, and a controller communicatively coupled to the sensor unit and the applicator. The controller is configured to receive the captured images, process the captured images for determining one or more characteristics of the plant stand, generate one or more control signals based on the one or more characteristics, and send the one or more control signals to the applicator. The applicator is configured to perform at least one action on the plant stand based on the one or more control signals. | 2019-10-10 |
20190311199 | ADAPTIVE SAMPLING OF TRAINING VIEWS - A head-mounted display, a method, and a non-transitory computer readable medium are provided. An embodiment of a method for obtaining training sample views of an object includes the step of storing, in a memory, multiple views of an object. The method also includes the step of deriving similarity scores between adjacent views and then a sampling density is varied based on the similarity scores. | 2019-10-10 |
20190311200 | CONTROL APPARATUS AND CONTROL METHOD FOR DETERMINING RELATION OF PERSONS INCLUDED IN AN IMAGE, AND STORAGE MEDIUM STORING A PROGRAM THEREFOR - A control apparatus includes a detection unit, an association unit, and an output control unit. The detection unit detects a person from an image which includes a plurality of persons. The association unit associates the persons included in the image with each other based on at least one of a position of the person detected by the detection unit, directions of faces of the persons included in the image, and distances between the persons included in the image. The output control unit causes an output unit to output information that is indicative of a relation of the detected person with respect to other persons included in the image based on a result of association performed by the association unit. | 2019-10-10 |
20190311201 | BATTERY-POWERED CAMERA WITH REDUCED POWER CONSUMPTION BASED ON MACHINE LEARNING AND OBJECT DETECTION - Apparatus and associated methods relate to transmitting video frames selected by a camera based on detected motion to a network hub configured with an artificial intelligence adapted to predict a region of interest within the selected video frames, configuring the camera with the region of interest predicted by the hub, and managing the energy consumption of the camera based on automatically governing camera operational parameters adapted as a function of the region of interest. In an illustrative example, the camera may be a battery-powered camera. In some embodiments, the camera may be configured in a low power mode with wireless interfaces off. In various implementations, the camera may be configured to detect motion within a region of interest and ignore motion elsewhere. Various examples may advantageously provide improved camera power management based on governing the camera operational parameters as a function of detected motion and the configured region of interest. | 2019-10-10 |
20190311202 | VIDEO OBJECT SEGMENTATION BY REFERENCE-GUIDED MASK PROPAGATION - Various embodiments describe video object segmentation using a neural network and the training of the neural network. The neural network both detects a target object in the current frame based on a reference frame and a reference mask that define the target object and propagates the segmentation mask of the target object for a previous frame to the current frame to generate a segmentation mask for the current frame. In some embodiments, the neural network is pre-trained using synthetically generated static training images and is then fine-tuned using training videos. | 2019-10-10 |
20190311203 | AERIAL MONITORING SYSTEM AND METHOD FOR IDENTIFYING AND LOCATING OBJECT FEATURES - An aerial monitoring system and method for identification and location of object features is disclosed. The aerial monitoring system and method includes training an image processing engine to identify predefined object features in images. Training involves the image processing engine generating a model for identifying predefined object features in images. Identifying the predefined object features includes using a drone outfitted with a drone camera to capture and geotag monitoring images of target objects. The monitoring images are both infrared and non-infrared. The image processing engine applies the model to the monitoring images to determine whether the monitoring images include object features that fit within one of multiple categories. The image processing engine uses a fuzzy clustering process to group objects into cluster locations. The image processing system outputs the identification and location of the object features. The output is used for maintenance planning related to the objects. | 2019-10-10 |
20190311204 | FOREGROUND DETECTOR FOR VIDEO ANALYTICS SYSTEM - Techniques are disclosed for creating a background model of a scene using both a pixel based approach and a context based approach. The combined approach provides an effective technique for segmenting scene foreground from background in frames of a video stream. Further, this approach can scale to process large numbers of camera feeds simultaneously, e.g., using parallel processing architectures, while still generating an accurate background model. Further, using both a pixel based approach and context based approach ensures that the video analytics system can effectively and efficiently respond to changes in a scene, without overly increasing computational complexity. In addition, techniques are disclosed for updating the background model, from frame-to-frame, by absorbing foreground pixels into the background model via an absorption window, and dynamically updating background/foreground thresholds. | 2019-10-10 |
20190311205 | METHOD, APPARATUS, AND SYSTEM FOR DETERMINING POLYLINE HOMOGENEITY - An approach is provided for an asymmetric evaluation of polygon similarity. The approach, for instance, involves receiving a first polygon representing an object depicted in an image. The approach also involves generating a transformation of the image comprising image elements whose values are based on a respective distance that each image element is from a nearest image element located on a first boundary of the first polygon. The approach further involves determining a subset of the plurality of image elements of the transformation that intersect with a second boundary of a second polygon. The approach further involves calculating a polygon similarity of the second polygon with respect the first polygon based on the values of the subset of image elements normalized to a length of the second boundary of the second polygon. | 2019-10-10 |
20190311206 | VEHICULAR VISION SYSTEM WITH AUXILIARY LIGHT SOURCE - A vehicular vision system includes a camera configured to be mounted at an in-cabin side of a windshield of a vehicle and having a field of view exterior and forward of the vehicle. An ECU includes an image processor operable to process image data captured by the camera when the camera is mounted at the vehicle windshield. The ECU, responsive at least in part to processing of captured image data, determines lane markers ahead of the vehicle. The ECU determines a path of travel of the vehicle. The ECU, responsive at least in part to processing of captured image data, detects an object that is present forward of the vehicle. Responsive to determination at the ECU that the detected object is in the path of travel of the vehicle, an auxiliary light source of the vehicle is controlled by the ECU to enhance illumination of the detected object. | 2019-10-10 |
20190311207 | VEHICLE CONTROL DEVICE, VEHICLE CONTROL METHOD, AND STORAGE MEDIUM - A vehicle control device includes a recognizer and a driving controller. The driving controller operates at least in one of a first control state and a second control state in which a automation rate is higher than the first control state or a lower level of task is required of an occupant than the first control state. The driving controller does not suppress operation in the second control state if a traffic sign recognized by the recognizer is a sign indicating a speed limit equal to or higher than a predetermined speed and suppresses operation in the second control state if the traffic sign is a sign indicating a speed limit less than the predetermined speed. | 2019-10-10 |
20190311208 | MACHINE-READABLE FORM CONFIGURATION AND SYSTEM AND METHOD FOR INTERPRETING AT LEAST ONE USER MARK - One embodiment of the present invention relates to a machine-readable form configuration (and associated method). Another embodiment of the present invention relates to a system for interpreting at least one user mark (and associated methods). In one example, a plurality of user marks may be interpreted. In another example, the machine-readable form may be a lottery play slip, survey, test, or the like. In another example, the system may interpret user mark(s) made on a lottery play slip, survey, test or the like. In another example, the system may interpret user mark(s) made on a paper or the like having non-planar distortion(s). | 2019-10-10 |
20190311209 | Feature Recognition Assisted Super-resolution Method - A vehicle mounted imaging system tracks and resolves image using an object image regions of interest at a higher resolution than that which can be provided by typical wide-angle optics. The imaging system includes an object identification camera, a sampling camera, and one or more computing devices. The one or more computing devices obtain a full-frame image from the object identification camera and identify at least one region of interest within the full frame image. The one or more computing devices then configure the sampling camera to capture images of a sampling area containing the region of interest, wherein the sampling area consists of some, but not all, of a field of view of the sampling camera. Using a super-image resolution technique, the one or more computing devices create a high-resolution image of the region of interest from a plurality of images captured by the sampling camera. | 2019-10-10 |
20190311210 | AUTOMATED EXTRACTION OF PRODUCT ATTRIBUTES FROM IMAGES - The system and method described herein provide for a machine-learning model to automate determination of product attributes for a product based on images associated with the product. The product attributes can be used in online commerce to facilitate product selection by a customer. In accordance with this disclosure, the product attributes may be determined using machine-learning technology by processing images associated with the product (including product packaging). The machine-learning technology is trained using product-related vocabulary and potential attributes that can be discovered by analyzing the images associated with the product. | 2019-10-10 |
20190311211 | APPARATUS FOR INSPECTING CHARACTERS/NUMBERS OF NEGOTIABLE INSTRUMENT, AND METHOD FOR INSPECTING CHARACTERS/NUMBERS OF NEGOTIABLE INSTRUMENT - An apparatus for inspecting the characters/numbers of a negotiable instrument, the apparatus being provided with: cameras ( | 2019-10-10 |
20190311212 | Method and System for Display the Data from the Video Camera - A system and method of video surveillance, namely, for processing of graphic and other video information for combination of display of the video images received from video cameras and data submitted a map of a given. The method including receiving an image from the video camera, defining a static object and coordinates of its location on a frame of the image and defining a mobile object and coordinates of its location on an image frame. Then setting a graphic symbol of a static object on map, calibrating the video camera and defining at least four virtual segments on the map and frame of the received image, and transforming coordinates of the static object from system of coordinates of a frame to a system of coordinates of the map, displaying a combination image on a display, and consecutively adjusting the transparency of the combined image. | 2019-10-10 |
20190311213 | Generating Feature Descriptors for Image Analysis - A computer-implemented method for generating a rotation-invariant feature descriptor for a location in an image for use in performing descriptor matching in analysing the image, extracts samples according to a descriptor pattern for the location in the image; uses the extracted samples to determine a measure of rotation for the location in the image, the measure of rotation describing an angle between an orientation of the image and a characteristic direction of the image at the location; generating a feature descriptor for the location in the image by determining a set of samples characterising the location in dependence on the determined measure of rotation and the extracted samples; and processes the determined set of samples to generate the feature descriptor for the location in the image. | 2019-10-10 |
20190311214 | Matching Local Image Feature Descriptors in Image Analysis - A method of feature matching in images captured from camera viewpoints uses the epipolar geometry of the viewpoints to define a geometrically-constrained region in a second image corresponding to a first feature in a first image; comparing the local descriptor of the first feature with local descriptors of features in the second image to determine respective measures of similarity; identifying, from the features located in the geometrically-constrained region, (i) a geometric best match and (ii) a geometric next-best match to the first feature; identifying a global best match to the first feature; performing a first comparison of the measures of similarity for the geometric best match and the global best match; performing a second comparison of the measures of similarity for the geometric best match and the geometric next-best match; and, if thresholds are met, selecting the geometric best match feature in the second image. | 2019-10-10 |
20190311215 | SYSTEMS AND METHODS FOR ADAPTIVE DATA PROCESSING ASSOCIATED WITH COMPLEX DYNAMICS - Systems and methods for adaptive data processing associated with complex dynamics are provided. The method may include applying the two or more predictive algorithms or rule-sets to an atomized model to generate applied data models. After receipt of inputs, the method may further include processing at least two propositions during a learning mode based upon detection of an absolute pattern within the applied data models; wherein propositions are action proposals associated with each predictive algorithm. At least two propositions may compete against each other through the use of an associated rating cell, which may be updated based upon the detected patterns. The method may further include processing propositions during an execution mode based upon detection of an absolute condition, wherein the rating cells are updated based upon these detected conditions. Further, these updated rating cells may be provided as feedback to update the atomized model. | 2019-10-10 |
20190311216 | IMAGE PROCESSING DEVICE, IMAGE PROCESSING METHOD, AND IMAGE PROCESSING PROGRAM - An image processing device | 2019-10-10 |
20190311217 | IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD, AND IMAGE CAPTURE APPARATUS - An image processing apparatus that is capable of improving subject detection accuracy with respect to image signals is disclosed. The image processing apparatus applies subject detection processing to an image by using a learning model generated based on machine learning. The image processing apparatus selects the learning model from a plurality of learning models stored in advance, in accordance with characteristics of the image to which the subject detection processing is to be applied. | 2019-10-10 |
20190311218 | SAMPLING FOR FEATURE DETECTION IN IMAGE ANALYSIS - A computer-implemented method for generating a feature descriptor for a location in an image for use in performing descriptor matching in analysing the image, the method comprising determining a set of samples characterising a location in an image by sampling scale-space data representative of the image, the scale-space data comprising data representative of the image at a plurality of length scales; and generating a feature descriptor in dependence on the determined set of samples. | 2019-10-10 |
20190311219 | QUASI-CLIQUE PROTOTYPE-BASED HYBRID CLUSTERING - Embodiments of the present disclosure describe a clustering scheme and system for partitioning a collection of objects, such as documents or images, using graph edges, identification of reliable cluster groups, and replacement of reliable cluster groups with prototypes to reconstruct a graph. The process is iterative and continues until the set of edges is reduced to a predetermined value. | 2019-10-10 |
20190311220 | Improvements To Computer Based Reasoning and Artificial Intellignence Systems - Techniques are provided herein for creating well-balanced computer-based reasoning systems and using those to control systems. The techniques include receiving a request to determine whether to use one or more particular data elements, features, cases, etc. in a computer-based reasoning model (e.g., as data elements, cases or features are being added, or as part of pruning existing features or cases). Conviction measures (such as targeted or untargeted conviction, contribution, surprisal, etc.) are determined and inclusivity conditions are tested. The result of comparing the conviction measure can be used to determine whether to include or exclude the feature, case, etc. in the computer-based reasoning model. A controllable system may then be controlled using the computer-based reasoning model. Examples controllable systems include self-driving cars, image labeling systems, manufacturing and assembly controls, federated systems, smart voice controls, automated control of experiments, energy transfer systems, health care systems, cybersecurity systems, and the like. | 2019-10-10 |
20190311221 | Low- And High-Fidelity Classifiers Applied To Road-Scene Images - Disclosures herein teach applying a set of sections spanning a down-sampled version of an image of a road-scene to a low-fidelity classifier to determine a set of candidate sections for depicting one or more objects in a set of classes. The set of candidate sections of the down-sampled version may be mapped to a set of potential sectors in a high-fidelity version of the image. A high-fidelity classifier may be used to vet the set of potential sectors, determining the presence of one or more objects from the set of classes. The low-fidelity classifier may include a first Convolution Neural Network (CNN) trained on a first training set of down-sampled versions of cropped images of objects in the set of classes. Similarly, the high-fidelity classifier may include a second CNN trained on a second training set of high-fidelity versions of cropped images of objects in the set of classes. | 2019-10-10 |
20190311222 | EVALUATION SYSTEM, EVALUATION METHOD, AND EVALUATION PROGRAM - An evaluation system | 2019-10-10 |
20190311223 | IMAGE PROCESSING METHODS AND APPARATUS, AND ELECTRONIC DEVICES - Image processing methods, apparatuses, and electronic devices include: extracting features of an image to be processed to obtain a first feature map of the image; generating an attention map of the image based on the first feature map; fusing the attention map and the first feature map to obtain a fusion map; and extracting the features of the image again based on the fusion map. The implementation mode introduces an attention mechanism into image processing, and effectively improves the efficiency of acquiring information from an image. | 2019-10-10 |
20190311224 | DEVICES, SYSTEMS, AND METHODS FOR CLUSTERING REFERENCE IMAGES FOR NON-DESTRUCTIVE TESTING - Devices, systems, and methods obtain training images; generate image-alignment data based on the training images; cluster the training images based at least in part on the image-alignment data, thereby generating clusters of training images; and select one or more representative images from the training images based on the clusters of training images. | 2019-10-10 |
20190311225 | IMAGE AUTHENTICATION APPARATUS, METHOD, AND STORAGE MEDIUM USING REGISTERED IMAGE - An image authentication apparatus includes a registration unit, a parameter computing unit, a similarity degree calculation unit, a status acquisition unit, and a generation unit. The registration unit is configured to register an image of an object to be authenticated in a registration dictionary as a registered image. The parameter computing unit is configured to compute a parameter based on the registered image. The parameter is computed for a degree of similarity between an image of the object and the registered image. The similarity degree calculation unit is configured to calculate a degree of similarity between an image of the object and the registered image, using the parameter. The status acquisition unit is configured to acquire a registration status of the registered image. The generation unit is configured to generate a display screen including the registration status, and to output the generated display screen. | 2019-10-10 |
20190311226 | ENHANCED TRAINING INFORMATION GENERATION - Systems, methods, and non-transitory computer readable media configured to generate enhanced training information. Training information may be obtained. The training information may characterize behaviors of moving objects. The training information may be determined based on observations of the behaviors of the moving objects. Behavior information may be obtained. The behavior information may characterize a behavior of a given object. Enhanced training information may be generated by inserting the behavior information into the training information. | 2019-10-10 |
20190311227 | GENERATING SEARCHABLE TEXT FOR DOCUMENTS PORTRAYED IN A REPOSITORY OF DIGITAL IMAGES UTILIZING ORIENTATION AND TEXT PREDICTION NEURAL NETWORKS - The present disclosure relates to generating computer searchable text from digital images that depict documents utilizing an orientation neural network and/or text prediction neural network. For example, one or more embodiments detect digital images that depict documents, identify the orientation of the depicted documents, and generate computer searchable text from the depicted documents in the detected digital images. In particular, one or more embodiments train an orientation neural network to identify the orientation of a depicted document in a digital image. Additionally, one or more embodiments train a text prediction neural network to analyze a depicted document in a digital image to generate computer searchable text from the depicted document. By utilizing the identified orientation of the depicted document before analyzing the depicted document with a text prediction neural network, the disclosed systems can efficiently and accurately generate computer searchable text for a digital image that depicts a document. | 2019-10-10 |
20190311228 | CROSS-MODALITY IMAGE SYNTHESIS - A framework for cross-modality image synthesis. A first and second model may be trained using respective first and second pairs of complementary images and corresponding first and second ground truth images that represent first and second views of a region of interest. The first and second pairs of complementary images may be acquired by a first modality and the first and second ground truth images may be acquired by a second modality. A combinational network may further be trained to combine features from the first and second models. At least one synthetic second modality image may then be generated by passing current images through the trained first or second model and the combinational network, wherein the current images are acquired by the first modality and represent the first or second view of the region of interest. | 2019-10-10 |
20190311229 | Learning Models For Entity Resolution Using Active Learning - Methods, systems, and computer program products for learning models for entity resolution using active learning are provided herein. A computer-implemented method includes determining a set of data items related to a task associated with structured knowledge base creation, and outputting the set of data items to a user for labeling. Such a method also includes generating, based on a user-labeled version of the set of data items, a candidate model for executing the task, and one or more generalized versions of the candidate model. Additionally, such a method can also include generating a final model based on one or more iterations of analysis of the candidate model and analysis of the one or more generalized versions of the candidate model, and performing the task by executing the final model on one or more datasets. | 2019-10-10 |
20190311230 | GENERATING HYPERSPECTRAL IMAGE DATABASE BY MACHINE LEARNING AND MAPPING OF COLOR IMAGES TO HYPERSPECTRAL DOMAIN - Color images of food a user consumes, text information associated with the food and audio information associated with the food may be received. Color images are converted into hyperspectral images. A machine learning model classifies the hyperspectral images into features comprising at least taste, nutrient content and chemical composition. A database of food consumption pattern associated with the user is created based on classification features associated with the hyperspectral images, the text information and the audio information. A color image of local food may be received and converted into a hyperspectral image. The machine learning model is run with the hyperspectral image as input, and outputs classification features associated with the local food. Based on whether the classification features associated with the local food satisfies the food consumption pattern associated with the user, the local food may be recommended. | 2019-10-10 |
20190311231 | Multi-Perceptual Similarity Detection and Resolution - Embodiments relate to an intelligent computer platform to compute visual similarity across image objects. An object detection algorithm is utilized to identify image objects and to produce a tensor representation of the identified object. Multi-visual contextual similarity of the object is conducted to assess and determine related object images. A re-assessment of similarity is dynamically conducted in response to a product image selection. The re-assessment utilizes the tensor representations of the related object images, thereby conducting a mathematical assessment of similarity and object image identification. A final product is identified and selected based on the dynamic re-assessment and convergence on a directed outcome with minimal iterations of object interaction. | 2019-10-10 |
20190311232 | OBJECT TRACKING ASSISTED WITH HAND OR EYE TRACKING - Embodiments relate to tracking and determining a location of an object in an environment surrounding a user. A system includes one or more imaging devices and an object tracking unit. The system identifies an object in a search region, determines a tracking region that is smaller than the search region corresponding to the object, and scans the tracking region to determine a location associated with the object. The system may generate a ranking of objects, determine locations associated with the objects, and generate a model of the search region based on the locations associated with the objects. | 2019-10-10 |
20190311233 | LABEL-PRINTING CONTROL APPARATUS, NON-TRANSITORY COMPUTER-READABLE RECORDING MEDIUM AND LABEL-PRINTING CONTROL METHOD - Provided are a label-printing control apparatus, a non-transitory computer-readable recording medium and a label-printing control method. A hardware processor of the label-printing control apparatus creates an adjusting image, from a reference mark for determining a die-cutting position on a continuous label stock and a cut mark representing a shape to cut a label image printed on the continuous label stock, both extracted from print data, while arranging specific images each created from the cut mark, to be spaced apart from the respective reference marks with different distances in the adjusting image. The hardware processor further creates, from the reference mark and a label image extracted from the print data, an end product image including the reference mark and the label image, and instructs the label printing device to print the adjusting image and the end product image on a continuous label stock. | 2019-10-10 |
20190311234 | INFORMATION PROCESSING APPARATUS, METHOD, AND STORAGE MEDIUM - An information processing apparatus includes a memory device that stores instructions and at least one processor that executes the instructions to determine an image rendering instruction as a conversion target to be converted into a cutout rendering instruction among rendering instructions that have been input, convert the image rendering instruction that has been determined as the conversion target into a cutout rendering instruction, and generate a rendering command based on the rendering instructions that have been input and that include the cutout rendering instruction obtained by the conversion. | 2019-10-10 |
20190311235 | PORTABLE DUAL-INTERFACE DATA CARRIER WITH METAL FRAME - A portable dual-interface data carrier contains a metal sheet which can be provided with low technical effort and especially no ferrite material is required. The resulting portable dual-interface data carrier is more heavy than a state of the art PVC smart card and provides contact based interface on one side, whereas contactless interfaces is working from both sides of the card. One application domain of the data carrier is to provide a so-called smartcard. The present invention is furthermore directed towards a dual-interface module as well as towards a method for providing a portable dual-interface data carrier. Moreover, a data carrier is suggested comprising instructions for performing the suggested method and for manufacturing the portable dual-interface data carrier. | 2019-10-10 |
20190311236 | PORTABLE DUAL-INTERFACE DATA CARRIER WITH METAL FRAME - A portable dual-interface data carrier contains a metal sheet which can be provided with low technical effort and especially no ferrite material is required. The resulting portable dual-interface data carrier is more heavy than a state of the art PVC smart card and provides contact based interface on one side, whereas contactless interfaces is working from both sides of the card. One application domain of the data carrier is to provide a so-called smartcard. The present invention is furthermore directed towards a dual-interface module as well as towards a method for providing a portable dual-interface data carrier. Moreover, a data carrier is suggested comprising instructions for performing the suggested method and for manufacturing the portable dual-interface data carrier. | 2019-10-10 |
20190311237 | METHOD AND SYSTEM FOR PROVIDING AUTHENTICATED PRODUCT INFORMATION TO DISTRIBUTED DEVICES - The present teaching relates to method and system for providing information about a product. The method includes receiving, by a device of a user via a wireless connection when the device is near the product, a unique identifier from a near field communication (NFC) chip embedded in a tag attached to the product. The tag is constructed to embed an antenna, which breaks down upon a force being applied to tear the tag, and disables communication between the NFC chip and the device. The method forwards the unique identifier to a server that stores information about the product, and receives from the server the information about the product. The received information about the product is presented on the device to the user. | 2019-10-10 |
20190311238 | MULTILAYER COMPOSITE BACKED CARD - A transaction card is disclosed. The transaction card may include a first card component of non-plastic card material having a thickness of no more than about 0.3 mm, a second card component of composite fiber material having a thickness of no more than about 0.3 mm, and an adhesive for affixing the first layer and second layer together. The non-plastic card material may be selected from a group including wood, bamboo, steel, copper, aluminum, silver, gold, platinum, granite, marble, and slate and the composite fiber material may include at least one of a glass fiber composite, a carbon fiber composite, or a natural fiber composite. | 2019-10-10 |
20190311239 | NFC/RF Mechanism With Multiple Valid States for Detecting an Open Container, and Methods of Making and Using the Same - A wireless (e.g., near field or RF) communication device, and methods of manufacturing and using the same are disclosed. The wireless communication device includes a receiver and/or transmitter, a substrate with an antenna thereon, an integrated circuit, and one or more protection lines. The antenna receives and/or transmits or broadcasts a wireless signal. The integrated circuit processes the wireless signal and/or information therefrom, and/or generates the wireless signal and/or information therefor. The integrated circuit has a first set of terminals electrically connected to the antenna. The protection line(s) are on a common or different substrate as the antenna. The protection line(s) sense or determine a continuity state of a package or container on which the communication device is placed or to which the communication device is fixed or adhered, and are electrically connected to a second set of terminals of the integrated circuit different from the first set of terminals. | 2019-10-10 |
20190311240 | Authentication Hologram - An authentication system includes an object including an authentication hologram disposed over an area of a surface of the object. The authentication hologram is defined by a pattern of reflective material and includes latent authentication information. The system includes a computer-readable medium including program instructions for execution by one or more processors. The program instructions are executable by the one or more processors to: (i) receive, from an image capture device, a digital image of the authentication hologram, wherein light reflected by the reflective material is captured in the digital image of the authentication hologram, and (ii) detect the latent authentication information in the digital image of the authentication hologram, wherein an effect of the reflected light is reduced to detect the latent authentication information. | 2019-10-10 |
20190311241 | AUTOMOTIVE VIRTUAL PERSONAL ASSISTANT - The present disclosure relates to an automotive virtual personal assistant configured to provide intelligent support to a user, mindful of the user environment both in and out of a vehicle. Further, the automotive virtual personal assistant is configured to contextualize user-specific vehicle-based and cloud-based data to intimately interact with the user and predict future user actions. Vehicle-based data may include spoken natural language, visible and infrared camera video, as well as on-board sensors of the type commonly found in vehicles. Cloud-based data may include web searchable content and connectivity to personal user accounts, fully integrated to provide an attentive and predictive user experience. In contextualizing and communicating these data, the automotive virtual personal assistant provides improved safety and an enhanced user experience. | 2019-10-10 |
20190311242 | NEURAL NETWORK CONVOLUTION COMPUTATION METHOD AND DEVICE, AND COMPUTER-READABLE STORAGE MEDIUM - Aspects of a neural network convolution device are described herein. The aspects may include a matrix transformer and a matrix multiplication module. The matrix transformer may be configured to receive an input data matrix and a weight matrix, transform the input data matrix into a transformed input data matrix based on a first transformation matrix, and transform the weight matrix into a transformed weight matrix based on a second transformation matrix. The matrix multiplication module may be configured to multiply one or more input data elements in the transformed input data matrix with one or more weight elements in the transformed weight matrix to generate an intermediate output matrix. The matrix transformer may be further configured to transform the intermediate output matrix into an output matrix based on an inverse transformation matrix. | 2019-10-10 |
20190311243 | SYSTOLIC CONVOLUTIONAL NEURAL NETWORK - A circuit and method are provided for performing convolutional neural network computations for a neural network. The circuit includes a transposing buffer configured to receive actuation feature vectors along a first dimension and to output feature component vectors along a second dimension, a weight buffer configured to store kernel weight vectors along a first dimension and further configured to output kernel component vectors along a second dimension, and a systolic array configured to receive the kernel weight vectors along a first dimension and to receive the feature component vectors along a second dimension. The systolic array includes an array of multiply and accumulate (MAC) processing cells. Each processing cell is associated with an output value. The actuation feature vectors may be shifted into the transposing buffer along the first dimension and output feature component vectors may shifted out of the transposing buffer along the second dimension, providing efficient dataflow. | 2019-10-10 |
20190311244 | SPIKE NEURAL NETWORK CIRCUIT INCLUDING RADIATION SOURCE - Provided is a spike neural network circuit. The spike neural network circuit includes an axon configured to generate an input spike signal, a synapse including a first transistor for outputting a current according to a weight and a second transistor connected to the first transistor and outputting the current according to an input spike signal, a neuron configured to compare a value according to the current output from the synapse with a reference value and generate an output spike signal based on a comparison result, and a radiation source attached to a substrate on which the synapse is formed, configured to output radiation particles to the synapse, and configured to increase magnitudes of threshold voltages of the first and second transistors of the synapse. | 2019-10-10 |
20190311245 | DEEP LEARNING MODEL SCHEDULING - Systems, methods, and computer-executable instructions for determining a computation schedule for a recurrent neural network (RNN). A matrix multiplication (MM) directed-acyclic graph (DAG) is received for the RNN. Valid phased computation schedules for the RNN are generated. Each of the valid phase computation schedule includes an ordering of MM operations. For each of the plurality of valid phased computation schedules, each of the MM operations is partitioned to processor cores based on L3 cache to L2 cache data movement. The RNN is executed based on the valid phased computation schedules. A final computation schedule is stored. The final computation schedule is used for future executions of the RNN. | 2019-10-10 |
20190311246 | SYSTEM AND METHOD FOR DETERMINING AN ARTIFICIAL INTELLIGENCE MODEL IN A DECENTRALIZED NETWORK - A system may include a decentralized communication network and multiple processing devices on the network. Each processing device may have an artificial intelligence (AI) chip, the device may be configured to generate an AI model, determine the performance value of the AI model on the AI chip, receive a chain from the network where the chain contains a performance measure. If the performance value of the AI model is better than the performance measure, then the processing device may broadcast the AI model to the network for verification. If the AI model is verified by the network, the device may update the chain with the performance value so that the chain can be shared by the multiple processing devices on the network. Any processing device on the network may also verify an AI model broadcasted by any other device. Methods for generating the AI model are also provided. | 2019-10-10 |
20190311247 | SYSTEM AND METHOD FOR DETERMINING AN ARTIFICIAL INTELLIGENCE MODEL IN A DECENTRALIZED NETWORK - A system may include a decentralized communication network and multiple processing devices on the network. Each processing device may have an artificial intelligence (AI) chip, the device may be configured to generate an AI model, determine the performance value of the AI model on the AI chip, receive a chain from the network where the chain contains a performance measure. If the performance value of the AI model is better than the performance measure, then the processing device may broadcast the AI model to the network for verification. If the AI model is verified by the network, the device may update the chain with the performance value so that the chain can be shared by the multiple processing devices on the network. Any processing device on the network may also verify an AI model broadcasted by any other device. Methods for generating the AI model are also provided. | 2019-10-10 |
20190311248 | METHOD FOR RANDOM SAMPLED CONVOLUTIONS WITH LOW COST ENHANCED EXPRESSIVE POWER - A system and method for random sampled convolutions are disclosed to efficiently boost a convolutional neural network (CNN) expressive power without adding computation cost. The method for random sampled convolutions selects a receptive field size and generates filters with a subset of the receptive field elements, the number of learnable parameters, as being active, wherein the number learnable parameters corresponds to computing characteristics, such as SIMD capability, of the processing system upon which the CNN is executed. Several random filters may be generated, with each being run separately on the CNN. The random filter that causes the fastest convergence is selected over the others. The placement of the random filter in the CNN may be per layer, per channel, or per convergence operation. The CNN employing the random sampled convolutions method performs as well as other CNNs utilizing the same receptive field size. | 2019-10-10 |
20190311249 | IMAGE PROCESSING METHOD, IMAGE PROCESSING APPARATUS, AND COMPUTER-READABLE STORAGE MEDIUM - Provided are image processing method and apparatus for processing an input image using a convolutional neural network system, and a computer-readable storage medium. The convolutional neural network system that includes an input layer, an intermediate layer and an output layer, the image processing method includes: receiving the input image via the input layer; extracting image features of the input image via the intermediate layer; and outputting processing results for the input image via the output layer, wherein the intermediate layer includes at least one network block each of which includes a first convolutional layer, a first grouping rearrangement layer and a second convolutional layer that are cascaded. | 2019-10-10 |
20190311250 | NEURAL DEVICE OF PERFORMING CONDITIONED RESPONSE AND METHOD OF DRIVING THE SAME - A neural device to which a conditioned response function is imparted and a driving method thereof are disclosed. Quantum dots and a polymer insulating layer are formed between upper and lower electrodes. Conductive filaments are formed at interfaces between the quantum dots and the polymer insulating layer. When a positive pulse, which is an unconditioned stimulus signal, is applied, the conductive filaments are formed, and a low resistance state is implemented. As the number of applications of a negative pulse, which is a conditioned stimulus signal, increases, the neural device is switched from a high resistance state to the low resistance state. Through this, the neural device having learning ability for the conditioned stimulus signal may be implemented and driven. | 2019-10-10 |
20190311251 | INSTRUCTION GENERATION PROCESS MULTIPLEXING METHOD AND DEVICE - Aspects of reusing neural network instructions are described herein. The aspects may include a computing device configured to calculate a hash value of a neural network layer based on the layer information thereof. A determination unit may be configured to determine whether the hash value exists in a hash table. If the hash value is included in the hash table, one or more neural network instructions that correspond to the hash value may be reused. | 2019-10-10 |
20190311252 | MULTIPLICATION AND ADDITION DEVICE FOR MATRICES, NEURAL NETWORK COMPUTING DEVICE, AND METHOD - Aspects of a neural network operation device are described herein. The aspects may include a matrix element storage module configured to receive a first matrix that includes one or more first values, each of the first values being represented in a sequence that includes one or more bits. The matrix element storage module may be further configured to respectively store the one or more bits in one or more storage spaces in accordance with positions of the bits in the sequence. The aspects may further include a numeric operation module configured to calculate an intermediate result for each storage space based on one or more second values in a second matrix and an accumulation module configured to sum the intermediate results to generate an output value. | 2019-10-10 |
20190311253 | CONVOLUTIONAL NEURAL NETWORKS ON HARDWARE ACCELERATORS - A hardware acceleration component is provided for implementing a convolutional neural network. The hardware acceleration component includes an array of N rows and M columns of functional units, an array of N input data buffers configured to store input data, and an array of M weights data buffers configured to store weights data. Each of the N input data buffers is coupled to a corresponding one of the N rows of functional units. Each of the M weights data buffers is coupled to a corresponding one of the M columns of functional units. Each functional unit in a row is configured to receive a same set of input data. Each functional unit in a column is configured to receive a same set of weights data from the weights data buffer coupled to the row. Each of the functional units is configured to perform a convolution of the received input data and the received weights data, and the M columns of functional units are configured to provide M planes of output data. | 2019-10-10 |
20190311254 | TECHNOLOGIES FOR PERFORMING IN-MEMORY TRAINING DATA AUGMENTATION FOR ARTIFICIAL INTELLIGENCE - Technologies for performing in-memory training data augmentation for artificial intelligence include a memory comprising media access circuitry connected to a memory media. The media access circuitry is to obtain an input training data set that includes an initial amount of data samples that are usable to train a neural network. The media access circuitry is further to produce, from the input training data set, an augmented training data set with more data samples than the input training data set. | 2019-10-10 |
20190311255 | NEUROMORPHIC CODE PROCESSOR - Inspired by the processing methods of biologic brains, we construct a network of multiple configurable non-volatile memory arrays connected with bus-lines as a neuromorphic code processor for code processing. In contrast to the Von-Neumann computing architectures applying the multiple computations for code vector manipulations, the neuromorphic code processor of the invention processes codes according to their configured codes stored in the non-volatile memory arrays. Similar to the brain processor, the neuromorphic code processor applies the one-step feed-forward processing in parallel resulting in a dramatic power reduction compared with the computational methods in the conventional computer processors. | 2019-10-10 |
20190311256 | HYBRID NEUROMORPHIC COMPUTING DISPLAY - A hybrid neuromorphic computing device is provided, in which artificial neurons include light-emitting devices that provide weighted sums of inputs as light output. The output is detected by a photodetector and converted to an electrical output. Each neuron may receive output from one or more other neurons as initial input, allowing for high degrees of fan-out and fan-in, including true broadcast-to-all functionality. | 2019-10-10 |
20190311257 | COORDINATED HETEROGENEOUS PROCESSING OF TRAINING DATA FOR DEEP NEURAL NETWORKS - Systems and methods for training neural networks. One embodiment is a system that includes a memory configured to store samples of training data for a Deep Neural Network (DNN), and a distributor. The distributor identifies a plurality of work servers provisioned for training the DNN by processing the samples via a model of the DNN, receives information indicating Graphics Processing Unit (GPU) processing powers at the work servers, determines differences in the GPU processing powers between the work servers based on the information, and allocates the samples among the work servers based on the differences. | 2019-10-10 |
20190311258 | DATA DEPENDENT MODEL INITIALIZATION - Strategies for improved neural network fine tuning. Parameters of the task-specific layer of a neural network are initialized using approximate solutions derived by a variant of a linear discriminant analysis algorithm. One method includes: inputting training data into a deep neural network having an output layer from which output is generated in a manner consistent with one or more classification tasks; evaluating a distribution of the data in a feature space between a hidden layer and the output layer; and initializing, non-randomly, the parameters of the output layer based on the evaluated distribution of the data in the feature space. | 2019-10-10 |
20190311259 | Content-Specific Neural Network Distribution - According to the present disclosure, an apparatus includes at least one processor; and at least one memory including computer program code. The at least one memory and the computer program code are configured, with the at least one processor, to cause the apparatus to receive media content for streaming to a user device; to train a neural network to be overfitted to at least a first portion of the media content; and to send the trained neural network and the first portion of the media content to the user equipment. In addition, another apparatus includes at least one processor; and at least one memory including computer program code. The at least one memory and the computer program code are configured, with the at least one processor, to cause the apparatus to receive at least a first portion of media content and a neural network trained to be overfitted to the first portion of the media content; and to process the first portion of the media content using the overfitted neural network. | 2019-10-10 |
20190311260 | BEHAVIORAL BIOMETRIC FEATURE EXTRACTION AND VERIFICATION - Behavioral verification of user identity includes building a deep neural network for keystroke-based behavioral verification of user identity. The building includes receiving recorded keystroke events, each such recorded keystroke event including (i) an indication of whether the recorded keystroke event is a key press or a key release, (ii) a key identifier of the respective key pressed or released, and (iii) a timestamp of the recorded keystroke event. The building further includes performing pre-processing of the recorded keystroke events to provide data structures representing sequential key events for processing by a deep neural network to extract local patterns, and training the deep neural network using the data structures. The method also includes providing the trained deep neural network for keystroke-based behavioral verification of user identity based on determinate vectors output from the trained deep neural network. | 2019-10-10 |
20190311261 | BEHAVIORAL BIOMETRIC FEATURE EXTRACTION AND VERIFICATION - Behavioral verification of user identity includes building a deep neural network for gait-based behavioral verification of user identity. The building includes receiving movement data describing movement, in multiple dimensions, of computer system(s) of user(s), the movement data including sensor data acquired from sensor(s) of the computer system(s). The building further includes performing pre-processing of the movement data to provide processed movement data for processing by a deep neural network to extract local patterns, and training the deep neural network using the processed movement data. The method also includes providing the trained deep neural network for gait-based behavioral verification of user identity based on determinate vectors output from the trained deep neural network. | 2019-10-10 |
20190311262 | MACHINE LEARNING DEVICE, MACHINE LEARNING METHOD, ELECTRONIC CONTROL UNIT AND METHOD OF PRODUCTION OF SAME, LEARNED MODEL, AND MACHINE LEARNING SYSTEM - A learning use data set showing relationships among an engine speed, an engine load rate, an air-fuel ratio of the engine, an ignition timing of the engine, an HC or CO concentration of exhaust gas flowing into an exhaust purification catalyst and a temperature of the exhaust purification catalyst is acquired. The acquired engine speed, engine load rate, air-fuel ratio of the engine, ignition timing of the engine, and HC or CO concentration of the exhaust gas flowing into the exhaust purification catalyst are used as input parameters of a neural network and the acquired temperature of the exhaust purification catalyst is used as training data to learn a weight of the neural network. The learned neural network is used to estimate the temperature of the exhaust purification catalyst. | 2019-10-10 |
20190311263 | MEMRISTIVE LEARNING FOR NEUROMORPHIC CIRCUITS - Memristive learning concepts for neuromorphic circuits are described. In one example case, a neuromorphic circuit includes a first oscillatory-based neuron that generates a first oscillatory signal, a diode that rectifies the first oscillatory signal, and a synapse coupled to the diode and including a long-term potentiation (LTP) memristor arranged in parallel with a long-term depression (LTD) memristor. The circuit further includes a difference amplifier coupled to the synapse that generates a difference signal based on a difference between output signals from the LTP and LTD memristors, and a second oscillatory-based neuron electrically coupled to the difference amplifier that generates a second oscillatory signal based on the difference signal. The circuit also includes a feedback circuit that provides a feedback signal to the LTP and LTD memristors based on a difference or error between a target signal and the second oscillatory signal. | 2019-10-10 |
20190311264 | DEVICE AND METHOD FOR OBTAINING FUNCTIONAL VALUE, AND NEURAL NETWORK DEVICE - Aspects of activation function computation for neural networks are described herein. The aspects may include a search module configured to receive an input value. The search module may be further configured to identify a data range based on the received input value and an index associated with the data range. Meanwhile, a count value may be set to one. Further, the search module may be configured to identify a slope value and an intercept value that correspond to the input value. A computation module included in the aspects may be configured to calculate an output value based on the slope value, the intercept value and the input value. In at least some examples, the process may be repeated to increase the accuracy of the result until the count of the repetition reaches the identified index. | 2019-10-10 |
20190311265 | METHOD AND DEVICE FOR OBTAINING A SYSTEM FOR LABELLING IMAGES - This method comprises: obtaining a first module for labelling images by machine learning on the basis of a first training corpus; obtaining a second training corpus from the first training corpus, by replacing, in the first training corpus, each of a portion of first labels by a replacement label, two first labels being replaced by one and the same replacement label; obtaining a second module for labelling images by machine learning on the basis of the second training corpus; obtaining the system for labelling images comprising: a first upstream module obtained from a portion of the first module, a second upstream module obtained from a portion of the second module and a downstream module designed to provide a labelling of an image on the basis of first descriptive data provided by the first upstream module and of second descriptive data provided by the second upstream module. | 2019-10-10 |
20190311266 | DEVICE AND METHOD FOR ARTIFICIAL NEURAL NETWORK OPERATION - Aspects of data modification for neural networks are described herein. The aspects may include a data modifier configured to receive input data and weight values of a neural network. The data modifier may include an input data configured to modify the received input data and a weight modifier configured to modify the received weight values. The aspects may further include a computing unit configured to calculate one or more groups of output data based on the modified input data and the modifier weight values. | 2019-10-10 |
20190311267 | NOISE INJECTION TRAINING FOR MEMORY-BASED LEARNING - The system described herein can include neural networks with noise-injection layers. The noise-injection layers can enable the neural networks to be trained such that the neural networks are able to maintain their classification and prediction performance in the presence of noisy data signals. Once trained, the parameters from the neural networks with noise-injection layers can be used in the neural networks of systems that include resistive random-access memory (ReRAM), memristors, or phase change memory (PCM), which use analog signals that can introduce noise into the system. The use of ReRAM, memristors, or PCM can enable large-scale parallelism that improves the speed and computational efficiency of neural network training and classification. Using the parameters from the neural networks trained with noise-injection layers, enables the neural networks to make robust predictions and calculations in the presence of noisy data. | 2019-10-10 |
20190311268 | DEEP NEURAL NETWORKS MODELING - A promotion value model uses deep neural networks to learn to calculate the promotion value of a commercial brand. The model determines and reports the promotion value of a plurality of electronic media files each containing at least one commercial brand indicator. The learned model identifies the electronic media files and determines at least one context for each of the at least one commercial brand indicators. Promotion value is modeled with a deep neural network that maps the context for each of the commercial brand indicators to feature vectors mapped to an input layer of the neural network. Network parameters are learned to indicate relative weighted values between transitions of the layers of the neural network. | 2019-10-10 |
20190311269 | NON-LINEAR PROGRAMMING PROBLEM PROCESSING DEVICE AND NON-LINEAR PROGRAMMING PROBLEM PROCESSING METHOD - To efficiently process a programming problem including a function defined piecewise without having the differentiability and continuity of the function expressing the problem or spatial continuity as prerequisites, a non-linear programming problem processing device is provided with: a non-linear programming problem input unit; a provisional solution generation unit that produces a solution obtained in a certain region of the non-linear programming problem as a provisional solution; a solution candidate generation unit that produces a solution obtained in a nearby region of the provisional solution as a solution candidate; a provisional solution update unit that updates the solution candidate in accordance with the result of comparison of the provisional solution and the solution candidate; an end determination unit that determines the end of the process using a provisional solution improvement degree and/or the number of times of generation of the solution candidate; and a non-linear programming problem solution output unit. | 2019-10-10 |
20190311270 | Optimization of Over-The-Air File Distribution for Connected Cars Based Upon a Heuristic Scheduling Algorithm - Concepts and technologies disclosed herein are directed to the optimization of over-the-air (“OTA”) file distribution for connected cars based upon a heuristic scheduling algorithm. A schedule provided by the heuristic scheduling algorithm is designed to distribute OTA data flow to connected cars over the network (geographically) and over a scheduling time horizon (timely), and is capable of reducing the negative impact of OTA file updates on overall wireless network performance. This schedule is created based upon historical statistics associated with connected car driving patterns and simulations of connected car-specific OTA traffic over the network. By leveraging connected cars that connect to different cells at different times based upon driving patterns, the heuristic scheduling algorithm is effective in reducing OTA impact on the network. | 2019-10-10 |