Abstract:
In this paper, a gender and age classification method, in which age is classified into four classes: child, youth, midlife and agedness, based on shape free texture and boosting learning is introduced. After a face is detected, face alignment extracts 88 facial landmarks by which the face image is normalized to a shape free texture. Further more, three kinds of local feature, Haar like feature, LBP histogram and Gabor jet are extracted from the shape free texture; and boosting learning method is used for training classifiers. The experimental results show that, LBP histogram can be used for robust recognition of children and old people, Haar like feature is more efficient for discriminating young and middle aged people, and Gabor Jet fits for gender classification best.