Neural Network-Based Face Detection

Abstract

We present a neural network?ased 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?ace training examples, which must be chosen to span the entire space of non?ace images. Comparisons with other state?f?he?rt face detection systems are presented; our system has better performance in terms of detection and false?ositive rates.