Gender recognition using fusion of spatial and temporal features

Abstract

In the paper, a gender recognition scheme has been proposed based on fusion of spatial and temporal features. As a first step, face from the image is detected using Viola Jones method and then spatial and temporal features are extracted from the detected face images. Spatial features are obtained using Principal Component Analysis (PCA) while Discrete Wavelet Transform (DWT) has been applied to extract temporal features. In this paper we investigate the fusion of both spatial and temporal features for gender classification. The feature vectors of test images are obtained and classified as male or female by Weka tool using 10 fold cross validation technique. To evaluate the proposed scheme FERET database has been used providing accuracy better than the individual features. Experimental result shows 9.77% accuracy improvement with respect to spatial domain recognition system. © Springer International Publishing Switzerland 2014.