Gender classification using KPCA and SVM
Anjali Goel, Virendra Prasad Vishwakarma · 2016
A new technique to construct feature vector for gender classification is proposed in this paper. Here, new feature reduction technique is used to remove the irrelevant features of images. Feature reduction also helps in reducing the over fitting problem of the dataset. KPCA is a kernel based PCA which maps data from original space to non-linear feature space. Kernel trick helps in reducing the expensive computation of mapping data to higher dimensional space. Optimal parameter of SVM C and Ύ are learned using cross validation dataset. Features obtained using KPCA are used to classify images into male or female using SVM. Images of different databases i.e. AT@T, Faces94 and Georgia Tech have been used to validate the efficiency of the proposed technique. Proposed technique has better generalization performance as compare to other existing techniques.