Heisele, B; Serre, T; Pontil, M; Vetter, T; Poggio, T; (2002) Categorization by learning and combining object parts. In: Dietterich, TG and Becker, S and Ghahramani, Z, (eds.) ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 14, VOLS 1 AND 2. (pp. 1239 - 1245). M I T PRESS
Full text not available from this repository.
We describe an algorithm for automatically learning discriminative components of objects 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 against 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 component-based classification experts and their combination, b) the use of 3-D morphable models for training, and c) a maximum operation on the output of each component classifier which may be relevant for biological models of visual recognition.
|Title:||Categorization by learning and combining object parts|
|Event:||15th Annual Conference on Neural Information Processing Systems (NIPS)|
|Dates:||2001-12-03 - 2001-12-08|
|UCL classification:||UCL > School of BEAMS > Faculty of Engineering Science > Computer Science|
Archive Staff Only: edit this record