A robust face detection system using evolving neural networks

This paper presents a robust and precise scheme for face detection and precise facial feature location which is based on neural network in combination with genetic algorithms (GA). GA is used to help to improve the tolerance of the neural networks against open faults. Unlike similar systems which are limited to detecting upright, frontal faces, this system detects faces at any degree of rotation in the image plane. Our system directly analyzes image intensities using neural networks, whose parameters are learned automatically from training examples. We add 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. The structural model is used to characterize the geometric pattern of facial components. 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.