Abstract—The term gait recognition is typically used to signify the identification of people in image sequences by the way they walk. Human gait is a valuable biometric cue that can be used for human identification besides other biometrics such as faces & fingerprints. Gait is determined by the physical characteristics of each individual, and so is believed to be as unique to the person as a fingerprint is. Gait is relatively new and emergent behavioral biometric, that pertains to the use of an individuals walking style to determine or validate identity. Human identification using gait is a challenging computer vision task. Gait is also one of the few biometrics that can be measured at a distance, which makes it useful in surveillance applications as well. In this paper, our objective is to develop robust methods for extracting discriminate gait features automatically and passively from low-resolution video. For this, we explore two gait recognition techniques. They are Image based gait recognition and Formula based gait recognition. Both methods characterize and recognize gait by computing correspondence-free motion features from the video sequence.

Cite: D. Sharmila and E. Kirubakaran, "Image and Formula Based Gait Recognition Methods," International Journal of Computer and Electrical Engineering vol. 2, no. 2, pp. 381-388, 2010.