Human visual recognition is based largely on shape, yet effectively using shapes in natural image retrieval is a challenging task. Most existing methods are based on the geometric...
In this paper, a novel automatic image annotation system is proposed, which integrates two sets of support vector machines (SVMs), namely the multiple instance learning (MIL)-base...
Computing correspondences between pairs of images is fundamental to all structures from motion algorithms. Correlation is a popular method to estimate similarity between patches o...
This paper presents a deformable model for automatically segmenting objects from volumetric MR images and obtaining point correspondences, using geometric and statistical informati...
In this paper we propose a novel approach to accurate face localisation for faces under Near-Infrared (Near-IR) illumination. The circular shape of the bright pupils is a scale an...