| ECVision indexed and annotated bibliography of cognitive computer vision publications This bibliography was created by Hilary Buxton and Benoit Gaillard, University of Sussex, as part of ECVision Specific Action 8-1 The complete text version of this BibTeX file is available here: ECVision_bibliography.bib
B. Heisele and T. Serre and M. Pontil and T. Vetter and T. Poggio
ABSTRACT
We describe an algorithm for automatically learning discriminative parts in object images with SVM classifiers. It is based on growing image parts by minimizing theoretical bounds on the error probability of an SVM. Component-based face classifiers are then combined in a second stage to yield a hierarchical SVM classifier. Experimental results in face classification show considerable robustness for rotations in depth and suggest performance at significantly better level than other face detection systems. Novel aspects of our approach are: a) an algorithm to learn from examples component-based classification experts and their combination, b) the use of 3D morphable models for training and c) a MAX operation -- on the output of each component classifier within a search region-- which may be relevant for biological models of visual recognition. |
|
| Site generated on Friday, 06 January 2006
|