Gender Recognition Based On Combining Facial and Hair Features

Abstract

This paper presents a gender recognition method by combining three types of effective features, including facial texture features, hair geometry features, and mustache features. The recognition method includes two phases which are based on the AdaBoost algorithm. In the first phase, facial and hair features are extracted from a face image and then fed into a classifier to roughly classify the image into male and female classes. In the second phase, the mustache features are added into the feature vector of the female patterns which classified into female class in the first phase. The female patterns are then classified again to correct the misclassified patterns. The FERET database is used to evaluate our method in the experiment. In the FERET data set, 659 images are chosen in which 366 of them are used as training data and the rest are regarded as test data. The best classification rate of the proposed method achieves 96.25%.