Efficient feature extraction using DCT for gender classification

In this paper, a new technique for constructing feature vector from DCT coefficients for gender classification has been presented. Firstly, images are divided into 8 × 8 sub images. DCT coefficients are calculated for each block in image. New technique is used for constructing the feature vector from DCT coefficients. Finally, SVM with Rbf kernel is used for classifying the images into male and female. Using 2-Fold cross validation, optimal value for SVM parameters are found. Images of AT@T, FACES94 and Georgia Tech face database images are used for evaluation of proposed technique and it is found that the proposed technique is better in terms of generalization performance and computational cost than that of other state-of-art techniques.