Most variational active contour models are designed to find the “desirable” local minima of data-dependent energy functionals with the hope of avoiding undesirable configurat...
Developing applications that make effective use of machine-readable knowledge sources as promised by the Semantic Web vision is attracting much of current research interest; this v...
Approximately 2 degrees in our 140 degree vision span has sharp vision. Many researchers have been fascinated by the idea of eyetracking integrated perceptual compression of an im...
Abstract. We propose a new method for face recognition under arbitrary pose and illumination conditions, which requires only one training image per subject. Furthermore, no limitat...
Most methods for the recognition of shape classes from 3D datasets focus on classifying clean, often manually generated models. However, 3D shapes obtained through acquisition tech...