Resumen
A biometric system offers automatic identification of an individual based on characteristic possessed by the individual. Biometric identification systems are often categorized as physiological or behavioural characteristics. Gait as one of the behavioural biometric recognition aims to recognize an individual by the way he/she walk. In this paper we propose gender classification based on human gait features using wavelet transform and investigates the problem of non-neutral gait sequences; Coat Wearing and carrying bag condition as addition to the neutral gait sequences. We shall investigate a new set of feature that generated based on the Gait Energy Image and Gait Entropy Image called Gait Entropy Energy Image (GEnEI). Three different feature sets constructed from GEnEI based on wavelet transform called, Approximation coefficient Gait Entropy Energy Image, Vertical coefficient Gait Entropy Energy Image and Approximation & Vertical coefficients Gait Entropy Energy Image Finally two different classification methods are used to test the performance of the proposed method separately, called k-nearest-neighbour and Support Vector Machine. Our tests are based on a large number of experiments using a well-known gait database called CASIA B gait database, includes 124 subjects (93 males and 31 females). The experimental result indicates that the proposed method provides significant results and outperform the state of the art.