Gait Based Human Recognition with Various Classifiers Using Exhaustive Angle Calculations in Model Free Approach

Abstract

Human Gait recognition is emerging as a supportive biometric technique in recent years that identifies the people through the way they walk. The gait recognition in model free approaches faces the challenges like speed variation, cloth variation, illumination changes and view angle variations which result in the reduced recognition rate. The proposed algorithm selected the exhaustive angles from head to toe of a person, and also height and width of the same subject. The experiments were conducted using silhouettes with view angle variation, and cloth variation. The recognition rate is improved to the extent of 91% using Support vector machine classifier . The proposed method is evaluated using CASIA Gait Dataset B (The institute of Automation, Chinese Academy of Sciences), China. Experimental results demonstrate that the proposed technique shows promising results using state of the art classifiers.