A preliminary study of gait-based age estimation techniques


Kek, Benz Yeo Chuen and Tee, Connie and Ong, Thian Song and Goh, Michael Kah Ong (2016) A preliminary study of gait-based age estimation techniques. In: 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA). IEEE, pp. 800-806. ISBN 978-9-8814-7680-7

[img] Text
Restricted to Repository staff only

Download (855kB)


Gait recognition is an emerging biometric technology due to the widespread use of closed-circuit television (CCTV) camera. Owing to the non-cooperative nature of CCTV setting, gait appears to be a valuable cue that can be extracted from the video footage. The gait feature extracted from the video can be used for several applications such as person authentication for security access control and walking pattern examination for medical analysis. In this paper, we explore the use of gait signature for age estimation. As this is a very new research area, there are not much gait-based age estimation techniques in the literature. Hence, this paper provides a study of the allied of works related to gait-based age estimation, ranging from medical to computer vision domains. Based on our study, several distinctive gait features that can be used for age estimation are identified. These features include stride length, stride frequency, head length, body length, head-to-body ratio, leg length and stature. Preliminary experiments conducted using the OU-ISIR Large Population gait database show that the proposed features could distinguish two age groups, namely adult and child, effectively.

Item Type: Book Section
Uncontrolled Keywords: Estimation, Feature extraction, Hidden Markov models, Face, Kinematics
Subjects: T Technology > TA Engineering (General). Civil engineering (General) > TA1501-1820 Applied optics. Photonics
Divisions: Faculty of Information Science and Technology (FIST)
Depositing User: Ms Rosnani Abd Wahab
Date Deposited: 04 Dec 2017 14:29
Last Modified: 04 Dec 2017 14:29
URII: http://shdl.mmu.edu.my/id/eprint/6539


Downloads per month over past year

View ItemEdit (login required)