Novel methods on Facial images for age classification and person identification

Abstract

As one of the most successful applications of image analysis and understanding, face recognition has recently received significant attention, especially in the recent past. There are at least two reasons for this trend; first is the wide range of commercial and law enforcement applications such as smart cards, access control, passports, credit cards, driving licenses, biometric authentication, video surveillance, and information security, among others and the second is the availability of feasible technologies after 30 years of research. The thesis mainly concentrated on textural properties of skin for face recognition and age classification. Initially facial properties are derived by exploring statistical texture features (STF) of co-occurrence matrices. A precise Face recognition is carried out on STF by a new distance function scheme that eliminates retrieved facial images based on significant texture features. One of the major drawback of most of the Face Recognition Methods are, they fail in recognizing the humans, if there is a variation in terms of age between probe and database facial image, because there will be significant changes in the face when a person acquires age. For this, a new direction for the child and adult classification using texture features derived from geometric properties of human face is proposed. The texture features of the present approach are computed from facial distance features. newlineThe advantage of the proposed approach is, it can be effectively used for persons with folded eye, blind, wearing spectacles, and face images with closed eyes. Generally the bone structural changes do not occur after the person is fully grown that is the geometric relationships of primary features do not vary. To extend the age classification problem further, secondary features based on Topological Texture Features in the facial skin are identified and exploited in the present study.