Feature Reduction and Hierarchy of Classifiers for Fast Object Detection in Video Images
Lists
Only you see this
Abstract
We present a two-step method to speed-up object detection systems in computer vision that use Support Vector Machines (SVMs) as classifiers. In a first step we perform feature reduction by choosing relevant image features according to a measure derived from statistical learning theory. In a second step we build a hierarchy of classifiers. On the bottom level, a simple and fast classifier analyzes the whole image and rejects large parts of the background On the top level, a slower but more accurate classifier performs the final detection. Experiments with a face detection system show that combining feature reduction with hierarchical classification leads to a speed-up by a factor of 170 with similar classification performance.
BibTeX
@inproceedings{heisele2001feature,
author = {Bernd Heisele and Thomas Serre and Sayan Mukherjee and Tomaso A. Poggio},
title = {{Feature Reduction and Hierarchy of Classifiers for Fast Object Detection in Video Images}},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2001},
doi = {10.1109/cvpr.2001.990919},
}Loading related content...