Pca-based Face Recognition Research

Techniques for face recognition were proposed by Francis Gallon as early as 1888[1]. In recent years considerable progress has been made in the area of face recognition. Through the development of techniques like Eigenfaces computers can now outperform humans in many face recognition tasks, particularly those in which large databases of faces must be searched. Whilst these methods performs extremely well under constrained conditions, the problem of face recognition under gross variations remains largely unsolved. This thesis details the PCA(Principle Component Analysis) algorithm and the development of a real-time face recognition system aimed to operate in constrained environments. Work in this thesis including:a) Preprocessing of face images on FERET face database[85], the preprocessing method including: geometric normalization, masking, histogram equalization, pixel normalization. Two different scale normalization methods also discussed, i.e. gray image interpolation and wavelet decomposition.b) Theory of PCA algorithm and its application to face recognition. A great many of experiments have been taken on ORL, Yale, FERET face database, analysis of the results leads to many meaning conclusions on how to improve recognition ration.c) Implemented a real-time face recognition system based on PCA algorithm.