VLFeat is an open and portable library of computer vision algorithms. It aims at facilitating fast prototyping and reproducible research for computer vision scientists and student...
Large quantities of documents in the Internet and digital libraries are simply scanned and archived in image format, many of which are packed in PDF files. The word search tool pr...
In this paper, we consider the problem of speaker verification as a two-class object detection problem in computer vision, where the object instances are 1-D short-time spectral v...
This paper presents a 3D approach to multi-view object class detection. Most existing approaches recognize object classes for a particular viewpoint or combine classifiers for a f...
The retinex algorithm for lightness and color constancy is extended to include 3-dimensional spatial information reconstructed from a stereo image. A key aspect of traditional ret...