Active Testing for Face Detection and Localization
Computer Vision and Pattern Recognition
2016-11-15 v1
Abstract
We provide a novel search technique, which uses a hierarchical model and a mutual information gain heuristic to efficiently prune the search space when localizing faces in images. We show exponential gains in computation over traditional sliding window approaches, while keeping similar performance levels.
Cite
@article{arxiv.1003.5249,
title = {Active Testing for Face Detection and Localization},
author = {Raphael Sznitman and Bruno Jedynak},
journal= {arXiv preprint arXiv:1003.5249},
year = {2016}
}
Comments
16 pages, 5 figures, accepted in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2010