We describe the g-factor which relates probability distributions on image features to distributions on the images themselves. The g-factor depends only on our choice of features a...
Recent work has shown impressive transform-invariant modeling and clustering for sets of images of objects with similar appearance. We seek to expand these capabilities to sets of...
A layered depth image (LDI) is a new popular representation and rendering method for objects with complex geometries. Similar to a 2D image, the LDI consists of an array of pixels...
We present a two-step method to speed-up object detection systems in computer vision that use Support Vector Machines (SVMs) as classifiers. In a first step we perform feature red...
Bernd Heisele, Thomas Serre, Sayan Mukherjee, Toma...
Abstract. Watermarking stays the main technical safeguard of electronic copyright. This paper presents the first public-domain oblivious watermarking scheme for images which survi...