Neural Networks for Face Recognition

Abstract

This chapter focuses on a neural network approach for pattern recognition. It gives an overview of the different attempts to apply ANN techniques to a variety of face recognition tasks. The chapter also describes critical elements of a typical face recognition system. Neural networks have been applied as pattern classifiers in a variety of fields including signal processing, speech recognition, image recognition, character recognition and dynamic systems. Face recognition has been studied for many years and has practical applications in areas such as security systems, identification of criminals and assistance with speech recognition systems. In face recognition an input image must be recognized regardless of its position, size, and angular orientation. Therefore, pattern recognition requires the nonlinear subdivision of the pattern space into subsets representing the objects to be identified. The transformation of images to their gradient equivalents prior to network training results in superior performance.