Patent application number | Description | Published |
20080238942 | Object-Based Image Inpainting - Systems and methods provide object-based image inpainting. The object-based inpainting can recover part of a missing object or can synthesize visual objects that are entirely missing. In one implementation, an exemplary system generates a target visual object to be inpainted into an image, by geometrically matching key features with a model visual object that can be selected from the same or another image. Borders of the target object are refined through pixel-based contour deformation and textures for the target object are obtained either by pixel interpolation or by patch-based modeling of pre-existing texture in the image. Graph-cut segmentation rectifies image overlap as the target object is embedded in the image. Poisson editing filters visual seams, and edge filling completes visual gaps around the border of the target object. | 10-02-2008 |
20080291065 | Wyner-Ziv Coding with Multiple Side Information - A Wyner-Ziv coding scheme jointly utilizes multiple side information at the decoder is described. A new probability model is introduced based on an extended turbo decoding trellis, so that the transitional probability is calculated from the probabilities conditioned on multiple side information. The proposed scheme handles multiple side information in a multi-dimensional manner to potentially achieve coding performance better than either selecting one side information or generating a single side information by averaging several side information. When the decoder receives multiple streams of parity bits, the conditional probabilities on the parity bits from the multiple streams all contribute in turbo decoding. The errors existing in some of the streams can be automatically eliminated during the decoding process. | 11-27-2008 |
20080292005 | Enhancement layer switching for scalable video coding - An exemplary system includes a data encoder generating a base layer bitstream encoded at a base bit-rate, and a plurality of enhancement layer bitstreams encoded at different enhancement layer bit-rates, and a bitstream selection module selecting one of the enhancement layer bitstreams every video frame based on available channel bandwidth. A method includes transmitting a first enhancement layer bitstream encoded at a first bit-rate, detecting a transition in network bandwidth through a switching bit-rate, and transmitting a second enhancement layer bitstream encoded at a second bit-rate based on the transition in network bandwidth. | 11-27-2008 |
20080319844 | Image Advertising System - Systems and methods are described for image advertising. In one implementation, an image owner registers an image-bearing medium, such as a website, device, email account, messenger account, printing service, etc., including proprietary images, with a service. The service may connect with the image-bearing medium, for example, by using a crawler to find and analyze images and surrounding text on the website or other image-bearing medium. Then a relevancy engine automatically matches each candidate image with one or more relevant advertisements, based on criteria such as visual image content, surrounding text, and textual/thematic description of the image from an automatic content analysis. The matched advertisements are displayed within or near the associated image, whenever the image is displayed or accessed, e.g., on the Internet. The advertisement owner may pay the image owner a monetary compensation, which in one implementation depends on the number of viewers who access the image. The systems and methods may be applied wherever images are displayed, copied, or transferred. | 12-25-2008 |
20090003712 | Video Collage Presentation - A method, a computer-readable storage media, and a user interface describe techniques for creating a video collage synthesized from video content, selecting representative images from the video content, extracting and resizing regions of interest (ROI) from the representative images from the video content, and arranging the regions of interest on a canvas without seams while preserving a temporal structure of the video content. The described method, computer-readable storage, and user interface enhance the experience of the user in browsing a video collage that is compact. | 01-01-2009 |
20090006368 | Automatic Video Recommendation - Automatic video recommendation is described. The recommendation does not require an existing user profile. The source videos are directly compared to a user selected video to determine relevance, which is then used as a basis for video recommendation. The comparison is performed with respect to a weighted feature set including at least one content-based feature, such as a visual feature, an aural feature and a content-derived textural feature. Multimodal implementation including multimodal features (e.g., visual, aural and textural) extracted from the videos is used for more reliable relevance ranking. One embodiment uses an indirect textural feature generated by automatic text categorization based on a set of predefined category hierarchy. Another embodiment uses self-learning based on user click-through history to improve relevance ranking. | 01-01-2009 |
20090103606 | Progressive Distributed Video Coding - Progressive distributed video coding is described. In one implementation, video data maybe encoded by arranging the data into bit-planes. The arrangement of bit-planes is adapted by shifting the first non-zero bit-plane left by one place in the binary digits and moving the sign bit immediately in the place vacated by the shifted non-zero bit-plane. The adapted bit-planes are then encoded using an asymmetric Slepian-Wolf encoder. | 04-23-2009 |
20090284650 | Bi-Level and Full-Color Video Combination for Video Communication - Systems and methods for video communication are described. In one aspect, network bandwidth conditions are estimated. Bi-level or full-color video is then transmitted over the network at transmission bit rates that are controlled as a function of the estimated bandwidth conditions. To this end, network bandwidth capability is periodically probed to identify similar, additional, or decreased bandwidth capabilities as compared to the estimated bandwidth conditions. Decisions to hold, decrease, or increase the video transmission bit rate are made based on the estimated bandwidth conditions in view of the probing operations. When the transmission bit rate is increased or decreased, the transmission bit rate is calculated to target an upper or lower bit rate, both of which are indicated by the estimated bandwidth conditions. Bi-level video communication is switched to full-color video transmission, or vice versa, when the video transmission bit rate respectively reaches the upper bit rate or the lower bit rate. | 11-19-2009 |
20090304298 | HIGH DYNAMIC RANGE TEXTURE COMPRESSION - A method for compressing a high dynamic range (HDR) texture. A first block of texels of the HDR texture in a red-green-blue (RGB) space may be transformed to a second block of texels in a luminance-chrominance space. The first block may have red values, green values and blue values. The second block may have luminance values and chrominance values. The chrominance values may be based on a sum of the red values, a sum of the green values and a sum of the blue values. The luminance values and the chrominance values may be converted to an 8-bit integer format. The luminance values may be modified to restore a local linearity property to the second block. The second block may be compressed. | 12-10-2009 |
20090315905 | LAYERED TEXTURE COMPRESSION ARCHITECTURE - Various technologies for a layered texture compression architecture. In one implementation, the layered texture compression architecture may include a texture consumption pipeline. The texture compression pipeline may include a processor, memory devices, and textures compressed at varying ratios of compression. The textures within the pipeline may be compressed at ratios in accordance with characteristics of the devices in the pipeline that contains and processes the textures. | 12-24-2009 |
20090322777 | UNIFIED TEXTURE COMPRESSION FRAMEWORK - A method for compressing textures. A first block of texels is transformed from a red-green-blue (RGB) space to a second block of texels in a luminance-chrominance space. The first block has red values, green values and blue values. The second block has luminance values and chrominance values. The chrominance values may be based on a sum of the red values, a sum of the green values and a sum of the blue values. The chrominance values may be sampled for a first subset of texels in the second block. The luminance values and the sampled chrominance values may be converted to an 8-bit integer format. The luminance values of the first subset may be modified to restore a local linearity property to the first subset. The second block may be compressed into a third block. | 12-31-2009 |
20100020882 | Barbell Lifting for Wavelet Coding - A method for encoding motion-compensated video data includes generating, for a current frame, a high-pass wavelet coefficient based on a function of pixels in a temporally adjacent frame. The operations are repeated for multiple pixels in an array of pixels in the current frame to form an array of high-pass wavelet coefficients. A low-pass wavelet coefficient is generated based on a function of the high-pass wavelet coefficients. A system for coding video data includes a temporal wavelet decomposition module decomposing a pixel into a high-pass coefficient by performing a discrete wavelet transform on the pixel, a function of pixels in a previous frame, and/or a function of pixels in a subsequent frame. The system includes a motion estimation module generating motion vectors associated with the pixels in the previous frame and in the subsequent frame. | 01-28-2010 |
20100142803 | Transductive Multi-Label Learning For Video Concept Detection - This disclosure describes various exemplary method and computer program products for transductive multi-label classification in detecting video concepts for information retrieval. This disclosure describes utilizing a hidden Markov random field formulation to detect labels for concepts in a video content and modeling a multi-label interdependence between the labels by a pairwise Markov random field. The process groups the labels into several parts to speed up a labeling inference and calculates a conditional probability score for the labels, the conditional probability scores are ordered for ranking in a video retrieval evaluation. | 06-10-2010 |
20100153219 | IN-TEXT EMBEDDED ADVERTISING - Computer program products, devices, and methods for generating in-text embedded advertising are described. Embedded advertising is “hidden” or embedded into a message by matching an advertisement to the message and identifying a place in the message to insert the advertisement. For textual messages, statistical analysis of individual sentences is performed to determine where it would be most natural to insert an advertisement. Statistical rules of grammar derived from a language model may be used choose a natural and grammatical place in the sentence for inserting the advertisement. Insertion of the advertisement creates a modified sentence without degrading a meaning of the original sentence, yet also includes the advertisement as a part of a new sentence. | 06-17-2010 |
20100158400 | Accelerated Screen Codec - An accelerated screen codec technique is described that provides a general screen compression framework, which, in one embodiment, is Graphics Processor Unit (GPU) friendly. In one embodiment, in order to compress screen data, blocks in a compound screen image containing both images and text are segmented into text blocks and pictorial blocks using a simple gradient-based procedure. The text and pictorial blocks are then compressed respectively via different compression techniques. Additionally, a GPU acceleration architecture of one embodiment of the accelerated screen codec technique provides a screen codec that maximally exploits a GPU's high parallelism and reduces the download bandwidth from GPU to Computer Processing Unit (CPU). | 06-24-2010 |
20110262049 | VISION-BASED COMPRESSION - Systems and methods provide vision-based image compression. In one implementation, inpainting is the vision-based technique selected to augment a conventional signal-processing-based technique. For some regions of a source image, an exemplary system efficiently extracts and organizes structural edge information instead of compressing the regions. In one implementation, the system applies binary curve fitting to capture the edge information. A structure-aware inpainter in the decoder can then restore the regions via the edge information, which occupies very little data space or minimal bandwidth in a bitstream that is transmitted from encoder to decoder. Key visual components of the image can still be conventionally compressed. Extracting edge information for some regions instead of compressing them considerably increases overall image compression. | 10-27-2011 |
20120117122 | Optimized KD-Tree for Scalable Search - Techniques for constructing an optimized kd-tree are described. In an implementation, an optimized kd-tree process receives input of a set of data points applicable for large-scale computer vision applications. The process divides the set of the data points into subsets of data points with nodes while generating hyperplanes (e.g., coordinate axes). The process identifies a partition axis for each node based on the coordinate axes combined in a binary way. The optimized kd-tree process creates an optimized kd-tree that organizes the data points based on the identified partition axis. The organization of the data points in the optimized kd-tree provides efficient indexing and searching for a nearest neighbor. | 05-10-2012 |
20120242674 | HIGH DYNAMIC RANGE TEXTURE COMPRESSION - A method for compressing a high dynamic range (HDR) texture. A first block of texels of the HDR texture in a red-green-blue (RGB) space may be transformed to a second block of texels in a luminance-chrominance space. The first block may have red values, green values and blue values. The second block may have luminance values and chrominance values. The chrominance values may be based on a sum of the red values, a sum of the green values and a sum of the blue values. The luminance values and the chrominance values may be converted to an 8-bit integer format. The luminance values may be modified to restore a local linearity property to the second block. The second block may be compressed. | 09-27-2012 |
20130179257 | In-Text Embedded Advertising - Computer program products, devices, and methods for generating in-text embedded advertising are described. Embedded advertising is “hidden” or embedded into a message by matching an advertisement to the message and identifying a place in the message to insert the advertisement. For textual messages, statistical analysis of individual sentences is performed to determine where it would be most natural to insert an advertisement. Statistical rules of grammar derived from a language model may be used choose a natural and grammatical place in the sentence for inserting the advertisement. Insertion of the advertisement creates a modified sentence without degrading a meaning of the original sentence, yet also includes the advertisement as a part of a new sentence. | 07-11-2013 |
20140037204 | Image Compression Based On Parameter-Assisted Inpainting - Systems and methods provide image compression based on parameter-assisted inpainting. In one implementation of an encoder, an image is partitioned into blocks and the blocks classified as smooth or unsmooth, based on the degree of visual edge content and chromatic variation in each block. Image content of the unsmooth blocks is compressed, while image content of the smooth blocks is summarized by parameters, but not compressed. The parameters, once obtained, may also be compressed. At a decoder, the compressed image content of the unsmooth blocks and the compressed parameters of the smooth blocks are each decompressed. Each smooth block is then reconstructed by inpainting, guided by the parameters in order to impart visual detail from the original image that cannot be implied from the image content of neighboring blocks that have been decoded. | 02-06-2014 |