Patent application number | Description | Published |
20080259799 | Packet Scheduling with Quality-Aware Frame Dropping for Video Streaming - The embodiments of the invention relate to video streaming, particularly to quality-aware adaptive and selective transmissions. The embodiments of the present invention provide for a set of scheduling patterns to be evaluated, and from such set determine the target scheduling pattern that is calculated to provide the least distortion increment based on the evaluation set. | 10-23-2008 |
20090028464 | IMAGE UPSCALING BASED UPON DIRECTIONAL INTERPOLATION - A method for interpolation includes receiving an input image having a plurality of pixels. The edge direction proximate a first pixel of the input image is estimated using a first technique from a plurality of discrete potential directions. An edge direction is selected based upon the estimating the edge direction proximate the first pixel of the input image using a second technique. The pixels proximate the first pixel are interpolated based upon the selected edge direction. The pixels proximate the first pixel are interpolated based upon another technique. An output image is determined pixels having more pixels than the plurality of pixels based upon step (d) and step (e). | 01-29-2009 |
20090244365 | SYSTEMS AND METHODS FOR INCREASING THE TEMPORAL RESOLUTION OF VIDEO DATA - A method for multi-scale spatio-temporal steering kernel regression may include repeatedly spatially downsampling input video data, thereby obtaining spatially downsampled video data at a coarsest spatial resolution scale. The spatially downsampled video data at the coarsest spatial resolution scale may be temporally upscaled to generate an estimate of temporally upscaled video data at the coarsest spatial resolution scale. The temporal upscaling may be achieved using spatio-temporal steering kernel regression. Estimates of the temporally upscaled video data may be repeatedly spatially upscaled to generate an estimate of the temporally upscaled video data at the original spatial resolution. The spatial upscaling may be achieved using spatio-temporal steering kernel regression. | 10-01-2009 |
20100245670 | SYSTEMS AND METHODS FOR ADAPTIVE SPATIO-TEMPORAL FILTERING FOR IMAGE AND VIDEO UPSCALING, DENOISING AND SHARPENING - A method for adaptive spatio-temporal filtering is disclosed. Local motion vectors between a current video frame and other nearby video frames are determined. Local motion-aligned temporal confidence parameters are determined. Local spatial orientation parameters are determined. The local motion vectors, the local motion-aligned temporal confidence parameters, and the local spatial orientation parameters are used to adaptively determine spatio-temporal kernel weights. The spatio-temporal kernel weights are used to perform spatio-temporal filtering on input video data. | 09-30-2010 |
20120075505 | CAMERA NOISE REDUCTION FOR MACHINE VISION SYSTEMS - A method for reducing noise in an image from an image capture device includes filter the image using both an offset fixed pattern noise filter and a gain fixed pattern noise filter. Thereafter, the image is filtered using a remnant fixed pattern noise filter to reduce remnant fixed pattern noise. | 03-29-2012 |
20120075535 | EFFICIENT MOTION VECTOR FIELD ESTIMATION - A system for producing a motion vector field for a current frame, where the system includes an estimator that selects an initial motion vector from a set of candidate motion vectors and a refiner that refines the initial motion vector. | 03-29-2012 |
20120263376 | SUPERVISED AND SEMI-SUPERVISED ONLINE BOOSTING ALGORITHM IN MACHINE LEARNING FRAMEWORK - A method for classification of samples comprising providing a trained statistical model based upon a set of initial samples. Receiving a set of first samples and training a first statistical model base upon the first set of samples, where the first statistical model is of the same class as the trained statistical model. Receiving a set of second samples and training a second statistical model base upon the second set of samples, where the second statistical model is of the same class as the trained statistical model. The trained statistical model, the first statistical model, and the second statistical model, being independent of each other and collectively used to classify another sample. | 10-18-2012 |
20130058582 | EDGE BASED TEMPLATE MATCHING - A system for image processing includes determining edge pixels of a model image using an edge based technique, and an angular orientation for each of the edge pixels of the model image. The system determines a lower spatial resolution model image based upon the model image and determining respective angular orientations for the lower spatial resolution model image, and determines edge pixels of an input image using an edge based technique, and an angular orientation for each of the edge pixels of the input image. The system determines a lower spatial resolution input image based upon the input image and determining respective angular orientations for the lower spatial resolution input image, and matches the lower spatial resolution model image with the lower spatial resolution input image to determine candidate locations of an object within the image and based upon the candidate locations matching the input image with the model image. | 03-07-2013 |
20130129188 | ELECTRONIC DEVICES FOR DEFECT DETECTION - An electronic device configured for defect detection is described. The electronic device includes a processor and instructions stored in memory that is in electronic communication with the processor. The electronic device performs background suppression on the image data based on a transform of the image data to obtain a score map. The electronic device also applies thresholding to the score map to generate a detection mask. The thresholding comprises bi-thresholding. The electronic device additionally detects any defects based on the detection mask. The electronic device further indicates any defects. | 05-23-2013 |
20130195365 | EDGE BASED TEMPLATE MATCHING - A method for image processing includes determining edge pixels of a model image and determining features for the edge pixels of the model image. The image processing includes determining edge pixels of an input image and determining features for the edge pixels of the input image. The system matches the features of the model image with the features of the input image to determine candidate locations of an object within the input image. | 08-01-2013 |
20130322772 | EDGE BASED LOCATION FEATURE INDEX MATCHING - A system for image processing that matches a model image with an input image. The matching process includes using a feature location index for the model image. | 12-05-2013 |
20140072217 | TEMPLATE MATCHING WITH HISTOGRAM OF GRADIENT ORIENTATIONS - A system for image processing includes determining edge pixels of a model image using an edge based technique and determining an angular orientation for each the edge pixels of the model image. The system determines a histogram of gradient orientations based upon the angular orientations of the model image. The system determining edge pixels of an input image using an edge based technique and determining an angular orientation for each of the edge pixels of the input image. The system determines a histogram of gradient orientations based upon the angular orientations of the input image. The system compares the histogram of gradient orientations of the model image with the histogram of gradient orientations of the input image to determine candidate locations of an object within the input image. | 03-13-2014 |
20140126839 | DEFECT DETECTION USING JOINT ALIGNMENT AND DEFECT EXTRACTION - A technique for image processing that includes receiving a model image, an input image, and registering the input image with the model image. A modified input image is determined that includes a first component that is substantially free of error components with respect to the model image and a second component that is substantially free of non-error aspects with respect to the model image. The technique determines an improved alignment of the modified input image with the model image where the improved alignment and the first and second components are determined jointly. | 05-08-2014 |
20140270347 | HIERARCHICAL IMAGE CLASSIFICATION SYSTEM - A technique for image processing that includes receiving a model image, an input image, and registering the input image with the model image. A modified input image is determined that includes a first component that is substantially free of error components with respect to the model image and a second component that is substantially free of non-error aspects with respect to the model image. The technique determines an improved alignment of the modified input image with the model image where the improved alignment and the first and second components are determined jointly. | 09-18-2014 |