In this paper we proposed a visual speech recognition network based on Support Vector Machines. Each word of the dictionary is modeled by a set of temporal sequences of visemes. E...
"Red-eye" is a phenomenon that causes the eyes of flash photography subjects to appear unnaturally reddish in color. Though commercial solutions exist for red-eye correc...
We recently proposed a method to find cluster structure in home videos based on statistical models of visual and temporal features of video segments and sequential binary Bayesian...
Daniel Gatica-Perez, Alexander C. Loui, Ming-Ting ...
This paper deals with some detection issues of watermark signals. We propose an easy way to implement an informed watermarking embedder whatever the detection function. This metho...
Teddy Furon, Benoit M. Macq, Neil J. Hurley, Gueno...
A supervised pixel-based classifier for identifying the presence of a given set of texture patterns of interest in a complex textured image is described. The proposed technique in...
This paper presents an efficient algorithm for post compression optimal rate allocation and packetization within JPEG2000 encoding. JPEG2000, the new ISO/ITU-T standard for still ...
In authentication using watermarking, the original media needs to be slightly modified in order to embed a short media digest in the media itself. Lossless authentication watermar...
One main focus of research in stereo image coding has been disparity estimation, a technique used to reduce the coding rate by taking advantage of the redundancy in a stereo image ...