Authors: K. Sugandhi; Farha Fatina Wahid; P. Nikesh; G. Raju
Addresses: Department of Information Technology, Kannur University, Kannur 670567, Kerala, India ' Department of Information Technology, Kannur University, Kannur 670567, Kerala, India ' School of Computer Sciences, Mahatma Gandhi University, Kottayam 686560, Kerala, India ' Department of Computer Science and Engineering, Faculty of Engineering, Christ University (Deemed to be University), Bengaluru 560074, Karnataka, India
Abstract: Identification of a person by his/her style of walking is referred as gait recognition. Gait is one among the biometric used for human identification. In gait recognition, an inevitable step for accurate feature extraction is gait cycle detection. In this paper, a novel gait cycle detection algorithm based on the concept of overlap between legs during locomotion is proposed. To identify overlap, zero-crossing counts of silhouette frames as well as bottom halves of silhouette frames are considered. The efficiency of this algorithm is tested using normal walking sequence of subjects with 90° viewing angle from CASIA B as well as TUM-IITKGP human gait databases. The results obtained shows that gait cycle can be easily and efficiently detected with zero-crossing count of silhouette frames. Further zero-crossing counts taken from bottom halves of silhouette frames gives better performance.
Keywords: gait; gait cycle; overlap; silhouette; zero-crossing.
International Journal of Biometrics, 2019 Vol.11 No.2, pp.148 - 159
Received: 22 Apr 2018
Accepted: 24 Oct 2018
Published online: 21 Mar 2019 *