Robust Method of Age Dependent Face Recognition

Abstract

This paper details our approach to building an automatic age determination algorithm based on age grouping. Face recognition has a variety of potential applications in public security, law enforcement and commerce such as identity authentication for credit card or driver license, access control, information security, and video surveillance, etc.. A good feature extraction will increase performance of face recognition system. This approach is based on the Principal Component Analysis (PCA). Eigen face approach is used for both age prediction and face recognition. The age prediction is carried out by projecting a new face image into this face space and then comparing its position in the face space with those of known faces. It will be reduced the time complexity using this approach. The proposed method preserves the identity of the subject while enforcing a realistic recognition effects on adult facial images between 15 to 60 years old and divided into 11 classes with 5 years old range. The accuracy of the system is analyzed by the variation on the range of the age groups. The efficiency of the system can be confirmed through the experimental results. The experiment results have confirmed the benefits of the association geometric feature based method and PCA method in facial feature extraction.