Title :
Gait-based person authentication by wearable cameras
Author :
Shiraga, Kohei ; Trung, Ngo Thanh ; Mitsugami, Ikuhisa ; Mukaigawa, Yasuhiro ; Yagi, Yasushi
Author_Institution :
Inst. of Sci. & Ind. Res., Osaka Univ., Ibaraki, Japan
Abstract :
In this paper, we propose a novel gait-based person authentication by wearable cameras, and quantitatively evaluate its authentication accuracy. In contrast to previous methods using motion sensors, we utilize wearable cameras for personal authentication by examining motion during walking obtained from visual information. This motion appears to provide a valid representation of the gait of the wearer. We then developed a prototype system of wearable surveillance, which is a new concept of surveillance we have proposed. The performance of our gait-based person authentication method was experimentally evaluated with 39 subjects using the prototype system, revealing an Equal Error Rate (EER) of 5.6%.
Keywords :
cameras; gait analysis; image motion analysis; image representation; video surveillance; EER; authentication accuracy; equal error rate; gait-based person authentication; motion sensor; visual information; wearable surveillance camera; Authentication; Cameras; Computers; Educational institutions; Estimation; Feature extraction; Prototypes;
Conference_Titel :
Networked Sensing Systems (INSS), 2012 Ninth International Conference on
Conference_Location :
Antwerp
Print_ISBN :
978-1-4673-1784-9
Electronic_ISBN :
978-1-4673-1785-6
DOI :
10.1109/INSS.2012.6240524