AT&T Intellectual Property I, LP

At+t Corp.

Leon Bottou

Patrick Guy Haffner

Steven Pigeon

Yoshua Bengio

Amy Ruth Reibman

Paul Glor Howard

Andrea Basso

Yann Andre LeCun

Patrice Y Simard

Andrea Bassi

Steven P Pigeon

A method, system, and machine-readable medium for classifying an image element as one of a plurality of categories, including assigning the image element based on a ratio between an unoccluded perimeter of the image element and an occluded perimeter of the image element and coding the image element according to a coding scheme associated with the category to which the image element is classified. Exemplary applications include image compression, where categories include image foreground and background layers.

Method and system for classifying image elements

A system, method and computer-readable media are introduced that relate to data coding and decoding. A computing device encodes received data such as video data into a base layer of compressed video and an enhancement layer of compressed video. The computing device controls drift introduced into the base layer of the compressed video. The computing device, such as a scalable video coder, allows drift bay predicting the base layer from the enhancement layer information. The amount of drift is managed to improve overall compression efficiency.

Scalable video encoder/decoder with drift control

A system, method and computer-readable media are introduced that relate to data coding and decoding. A computing device encodes received data such as video data into a base layer of compressed video and an enhancement layer of compressed video. The computing device controls drift introduced into the base layer of the compressed video. The computing device, such as a scalable video coder, allows drift by predicting the base layer from the enhancement layer information. The amount of drift is managed to improve overall compression efficiency.

System and method for processing data with drift control

Wavelet coding of partially-masked image information may be made faster by either of two embodiments of the present invention. In a first embodiment, quick convergence is obtained by performing wavelet encoding in stages, each stage associated with a predetermined wavelet scale. By advancing the stages from finest scale to coarsest scale, coefficients of masked wavelets are identifies early in the coding process. In a second embodiment, quick convergence is obtained by introducing overshoot techniques when masked coefficients are identified, modified and image data is reconstructed therefrom.

Compression of partially-masked image data

Scalable video coders have traditionally avoided using enhancement layer information to predict the base layer, so as to avoid so-called 'drift'. As a result, they are less efficient than a one-layer coder. The present invention is directed to a scalable video coder that allows drift, by predicting the base layer from the enhancement layer information. Through careful management of the amount of drift introduced, the overall compression efficiency can be improved while only slighly degrading resilience for lower bit-rates.

Growing community of inventors

Highlands, NJ, United States of America

Leon Bottou