Cascade of Gait Recognition with Surveillance System in a Client-Server Environment

要旨

This paper presents a system consisting of the application of gait recognition, a physiological biometric applied in a client-server environment. Now-a-days security plays a very important role in almost all fields and most of the public places like banks, airports, railway stations, etc., which require more security as the thieves and criminals are very intelligent whose objective is to create problems for human life and many untoward incidents. The gait recognition is a biometric used to identify an individual by their walking style. This has an advantage over other biometrics like face recognition because it is an unobtrusive biometric technique. In the early stage of preprocessing, an image is captured using image sensors and later segmentation is performed on the captured image to get foreground from a background. The segmented image is given as input to the Hough transform which generates a line base model from which gait features can be extracted and later gait can be recognized. Later, gait recognition of 10 subjects is stored in a gait database. A number of surveillance cameras with attached computers are connected to the gait database. If the camera identifies a subject in the given area whose gait is matching with the subject present in the gait database, it gives an alarm sound to the security department indicating the presence of a thief. so the security department can take necessary action. Keywords: Gait recognition, surveillance system, client-server environment, gait database, segmentation, Hough transform