Gender Classification Using Scaled Conjugate Gradient Back Propagation

Abstract

In this paper, we design an automated system that classifies gender by utilizing a set of human gait data. The gender classification system consists of four stages: in this method, firstly binary silhouette of a walking person is detected from each frame by using Eigen background method. Secondly, gait cycle is detected by using aspect ratio method. Thirdly, features from each frame in gait cycle are extracted by using: model free method. Finally, neural network are used for training and testing purposes. The experimental results on CASIA B database (12 males, 12 females) show that the proposed approach achieves a high accuracy in automatic gender classification. Project is designed by Matlab.