Face recognition is emerging as an active research area spanning many research branches such as image processing, pattern recognition, computer vision, and neural networks. Faces are one of the biometrics that humans often use in order to recognize individuals. Researchers have shown significant improvements in computing capability over the few decades, and nowadays enable to simulate similar recognitions automatically. In addition, face recognition technology has many commercial applications that range from static matching of controlled format photographs such as photos on identification cards to real time matching of video sequences. Although humans are remembering the faces quickly than other objects and seem to recognize faces easily, machine recognition is a complicated task. A general issue in this field is as follows: For a given image or video sequence, identify one or more person in the scene using a training database of faces. The solution of this issue involves segmentation of faces from non-face background objects, extraction of meaningful features from the face region, identification, and matching.

In this book, various state-of-art techniques about face recognition has been studied. The main portion of the book discuss about the face recognition system based on the probability distribution functions (PDF) of pixels in colour channels. This book studies into two main issues of face recognition, one of which is facial image illumination enhancement and the other one is classification stage where the face images are being recognized. In the pre-processing stage a novel facial image equalization method is studied and discussed. Further more PDF based face recognition is analytically is studied.

In this book, a new high performance face recognition system based on matching the colour pixel statistics is introduced. A pre-processing phase is introduced and applied to segment faces from the background. Furthermore, a dedicated image equalization method is introduced and implemented to minimize the illumination problems of the images for further processing. The histogram of the segmented face image as pixel statistics feature is used for face recognition by cross correlating the histogram of a given face and the histograms of faces in the database. Alternatively the probability distribution functions of the images in different colour channels, together with the Kullback-Leibler Divergence/Distance (KLD) metric is also used for the recognition of faces. Majority voting (MV) and feature vector fusion (FVF) methods is briefly introduced and applied to combine feature vectors obtained from different colour channels in HSI and YCbCr colour spaces to improve recognition performance.