Human Face Detection in Visual Scenes

A neural network-based face detection system that uses a bootstrap algorithm for training, which adds false detections into the training set as training progresses, and has better performance in terms of detection and false-positive rates than other state-of-the-art face detection systems.

Abstract

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 multiplenetworks to improveperformanceover asinglenetwork. We use a bootstrap algorithm for training, 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 another state-of-the-art face detection system are presented; our system has better performance in terms of detection and false-positive rates. 1