Patent application number | Description | Published |
20100194851 | PANORAMA IMAGE STITCHING - Systems and methods are disclosed for generation of a panoramic image of a scene. In an implementation, the method includes acquiring a plurality of images (e.g. first image and a second image) of the scene. Subsequent to image acquisition, the plurality of images is registered based on spatial relations of image data in an overlap region between the images. The spatial relations may correspond to distance and angle between a plurality of features in the first and the second images respectively. The registered images are merged based at least in part on a block based mean of the overlap region to generate the panoramic image. Block based merging is utilized to normalize spatially varying intensity differences of the first image and the second image. | 08-05-2010 |
20100195906 | AUTOMATIC IMAGE ENHANCEMENT - Disclosed is a method for correction of pixel values of an input image to compensate for variation in image capturing conditions is proposed. In an embodiment, the method enables computing a statistical value from a selected set of pixel values associated with the input image. Based, at least in part, on the computed statistical value a set of parameter values is derived. The parameter values correspond to at least two gompertz functions. The method further enables applying the at least two gompertz functions to the input image to obtain an output image. This results in an output image with one or more corrected pixel values. | 08-05-2010 |
20110182497 | CASCADE STRUCTURE FOR CLASSIFYING OBJECTS IN AN IMAGE - A cascade object classification structure for classifying one or more objects in an image is provided. The cascade object classification structure includes a plurality of nodes arranged in one or more layers. Each layer includes at least one parent node and each subsequent layer includes at least two child nodes. A parent node in a layer is operatively linked to two child nodes in a subsequent layer. Further, at least one child node in one of the subsequent layers is operatively linked to two or more parent nodes in a preceding layer. Each node includes classifiers for classifying the objects as a positive object and a negative object. The positive object and the negative object classified by the parent node in each layer are further classified by one or more operatively linked child nodes in the subsequent layer. | 07-28-2011 |
20140022337 | ROBUST TWO DIMENSIONAL PANORAMA GENERATION USING LIGHT FIELD CAMERA CAPTURE - A method, apparatus, and computer program product for generating a seamless and error-free panorama image using a selective set of views from a multi-view image from each of the several captured light field (LF) images. The method identifies the view and corresponding image for each captured LF image which has the same or closely located center of projection with the views of neighboring LF images. Image registration and warping techniques are applied across the images and the parallax error is calculated which indicates the closeness of their center of projections. The view from each LF captured image with minimal parallax error is selected and stitched together with the other views identified as having minimal parallax error. | 01-23-2014 |
20140028878 | METHOD, APPARATUS AND COMPUTER PROGRAM PRODUCT FOR PROCESSING OF MULTIMEDIA CONTENT - In accordance with an example embodiment a method, apparatus and computer program product are provided. The method comprises receiving a first image of a scene, the first image comprising angular information associated with the scene. The first image has a first image resolution. A second image of the scene is received. The second image has a second image resolution, wherein the second image resolution is greater than the first image resolution. A pre-processed first image is generated based on the angular information and a selection of a first region of interest (ROI) in the first image. A processed first image of the scene is generated based on a processing of a second ROI in the pre-processed first image corresponding to the first ROI in the first image, and the second image. The processing is configured to render the second image resolution to the second ROI in the pre-processed first image. | 01-30-2014 |
20140147050 | METHOD, APPARATUS AND COMPUTER PROGRAM PRODUCT FOR GENERATING SUPER-RESOLVED IMAGES - In an example embodiment a method, apparatus and computer program product are provided. The method includes facilitating receipt of a light-field image, determining one or more depth levels in the light-field image and generating a plurality of images from the light-field image. The method includes determining one or more registration matrices corresponding to the one or more depth levels between an image and one or more remaining images of the plurality of images. The method includes performing a super-resolution of the image and the one or more remaining images based on the one or more registration matrices to generate a super-resolved image of the image. | 05-29-2014 |
20140219575 | METHOD, APPARATUS AND COMPUTER PROGRAM PRODUCT FOR PROCESSING OF IMAGES - In accordance with an example embodiment a method, apparatus and computer program product are provided. The method comprises determining a plurality of first pixels having resemblance with a second pixel associated with an image based on a depth information of the image. The method further comprises replacing the second pixel by at least one first pixel of the plurality of first pixels based on a determination that the at least one first pixel is not associated with the at least one image defect. | 08-07-2014 |
20150010203 | METHODS, APPARATUSES AND COMPUTER PROGRAM PRODUCTS FOR PERFORMING ACCURATE POSE ESTIMATION OF OBJECTS - An apparatus for determining a pose(s) of an object(s) may include a processor and memory storing executable computer code causing the apparatus to at least perform operations including receiving a detected image of at least one face and analyzing the image of the at least one face based on data of at least one model identifying one or more poses. The poses may be related in part to at least one of a position or an orientation of respective faces. The computer program code may further cause the apparatus to determine that the face corresponds to one of the poses based in part on one or more items of data of the image passing criteria identified by the model as corresponding to the pose. Corresponding methods and computer program products are also provided. | 01-08-2015 |
20150033017 | Methods and Apparatuses for Electronic Message Authentication - Various methods are provided for facilitating the message recipient authentication using facial detection. One example method may include receiving a message. The message may include a plurality of encoded facial features that identify a message recipient. The method may further include causing an image to be captured of the message recipient in an instance in which the message is accessed. The method may also include authenticating the message recipient based on the captured image and the received plurality of encoded features provided with the received message. Similar and related example apparatuses and example computer program products are also provided. | 01-29-2015 |
20150060645 | METHOD, APPARATUS AND COMPUTER PROGRAM PRODUCT FOR SENSING OF VISIBLE SPECTRUM AND NEAR INFRARED SPECTRUM - In accordance with an example embodiment a method, apparatus and computer program product are provided. The method comprises filtering incident light by an IR cut-off filter to generate filtered light. The IR cut-off filter comprises a plurality of pixels with pass-band characteristics for visible light wavelengths and is configured to perform stop-band attenuation of near infrared (NIR) wavelengths. The stop-band attenuation is configured to vary based on spatial location of pixels within the IR cut-off filter. The filtered light received from the IR cut-off filter is sensed by the image sensor to generate sensed light. A baseband signal and a modulated NIR signal are determined by performing transformation of the sensed light. A NIR spectrum associated with the incident light is determined by demodulating the modulated NIR signal. A visible spectrum associated with the incident light is determined based on the NIR spectrum and the baseband signal. | 03-05-2015 |