Hierarchical classification and feature reduction for fast face detection with support vector machines

We present a two-step method to speed-up object detection systems in computer vision that use support vector machines as classi ers. In the rst step we build a hierarchy of classi ers. On the bottom level, a simple and fast linear classi er analyzes the whole image and rejects large parts of the background. On the top level, a slower but more accurate classi er performs the nal detection. We propose a new method for automatically building and training a hierarchy of classi ers. In the second step we apply feature reduction to the top level classi er by choosing relevant image features according to a measure derived from statistical learning theory. Experiments with a face detection system show that combining feature reduction with hierarchical classi cation leads to a speed-up by a factor of 335 with similar classi cation performance. ? 2003 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.