Graphics enhanced version of this site
Neural Network-Based Face Detection
H. Rowley, S. Baluja, and T. Kanade
Proceedings of the 1996 DARPA Image Understanding Workshop, February, 1996.
Jump to: Download | Abstract | Notes | Text Reference | BibTeX Reference
Adobe portable document format (pdf) [773 KB]
Compressed postscript (ps.gz) [2475 KB]
Compressed postscript (ps.z) [2660 KB]
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.
We present a neural network-based face detection system. A retinally connected neural network examines small windows of an image, and decides whether each window contains a face. The system arbitrates between multiple networks to improve performance over a single network. We use a bootstrap algorithm for training the networks, which adds false detections into the training set as training progresses. This eliminates the difficult task of manually selecting non-face training examples, which must be chosen to span the entire space of non-face images. Comparisons with other state-of-the-art face detection systems are presented; our system has better performance in terms of detection and false-positive rates.
Associated center: VASC
Associated labs/groups: Face Group and Human Sensing
Associated projects: Neural Network-Based Face Detection, Face Detection Databases, Face Detection, and Face Databases
H. Rowley, S. Baluja, and T. Kanade, "Neural Network-Based Face Detection," Proceedings of the 1996 DARPA Image Understanding Workshop, February, 1996.
@inproceedings{Rowley_1996_2679,
author = "Henry Rowley and Shumeet Baluja and Takeo Kanade",
title = "Neural Network-Based Face Detection",
booktitle = "Proceedings of the 1996 DARPA Image Understanding Workshop",
month = "February",
year = "1996"
}