Most image registration problems are formulated in an asymmetric fashion. Given a pair of images, one is implicitly or explicitly regarded as a template, and warped onto the other...
Subspace methods such as PCA, LDA, ICA have become a standard tool to perform visual learning and recognition. In this paper we propose Representational Oriented Component Analysi...
Fernando De la Torre, Ralph Gross, Simon Baker, B....
Non-linear subspaces derived using kernel methods have been found to be superior compared to linear subspaces in modeling or classification tasks of several visual phenomena. Such...
This work describes an approach for face detection, which is the rst stage of any fully automatedhumanface recognition system. We propose several enhancements to a feature-based ap...
Thispaper addresses theproblem in mug shot searching in suspect database. The objective is to improve the eficiency of the suspect identificationprocess. The input is a sketch con...