Author:
Park Gunwoo,Lee Kyoung Min,Koo Seungbum
Abstract
AbstractGait, the style of human walking, has been studied as a behavioral characteristic of an individual. Several studies have utilized gait to identify individuals with the aid of machine learning and computer vision techniques. However, there is a lack of studies on the nature of gait, such as the identification power or the uniqueness. This study aims to quantify the uniqueness of gait in a cohort. Three-dimensional full-body joint kinematics were obtained during normal walking trials from 488 subjects using a motion capture system. The joint angles of the gait cycle were converted into gait vectors. Four gait vectors were obtained from each subject, and all the gait vectors were pooled together. Two gait vectors were randomly selected from the pool and tested if they could be accurately classified if they were from the same person or not. The gait from the cohort was classified with an accuracy of 99.71% using the support vector machine with a radial basis function kernel as a classifier. Gait of a person is as unique as his/her facial motion and finger impedance, but not as unique as fingerprints.
Funder
Ministry of Science and ICT, South Korea
Ministry of Science and ICT
Publisher
Springer Science and Business Media LLC
Reference41 articles.
1. Seckiner, D., Mallett, X., Maynard, P., Meuwly, D. & Roux, C. Forensic gait analysis—Morphometric assessment from surveillance footage. Forensic Sci. Int. 296, 57–66 (2019).
2. Sabhanayagam, T., Venkatesan, V. P. & Senthamaraikannan, K. A comprehensive survey on various biometric systems. Int. J. Appl. Eng. Res. 13(5), 2276–2297 (2018).
3. Dargan, S. & Kumar, M. A comprehensive survey on the biometric recognition systems based on physiological and behavioral modalities. Expert Sys. Appl. 143, 113114 (2020).
4. Jain, A. K., Ross, A. & Prabhakar, S. An introduction to biometric recognition. IEEE Trans. Circuits Syst. Video Technol. 14(1), 4–20 (2004).
5. Connor, P. & Ross, A. Biometric recognition by gait: A survey of modalities and features. Comput. Vis. Image Underst. 167, 1–27 (2018).
Cited by
10 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献