IRMA-International.org: Creator of Knowledge
Information Resources Management Association
Advancing the Concepts & Practices of Information Resources Management in Modern Organizations

A Machine Learning Method with Threshold Based Parallel Feature Fusion and Feature Selection for Automated Gait Recognition

A Machine Learning Method with Threshold Based Parallel Feature Fusion and Feature Selection for Automated Gait Recognition
View Sample PDF
Author(s): Muhammad Sharif (Department of CS, COMSATS University Islamabad, Wah Campus, Wah Cantt, Pakistan), Muhammad Attique (Department of Computer Science, HITEC University, Museum Road Taxila, Pakistan), Muhammad Zeeshan Tahir (Department of CS, COMSATS University Islamabad, Wah Campus, Wah Cantt, Pakistan), Mussarat Yasmim (Department of CS, COMSATS University Islamabad, Wah Campus, Wah Cantt, Pakistan), Tanzila Saba (Artificial Intelligence & Data Analytics (AIDA) Lab, CCIS Prince Sultan University, Riyadh, Saudi Arabia) and Urcun John Tanik (Texas A&M University-Commerce, Commerce, USA)
Copyright: 2020
Volume: 32
Issue: 2
Pages: 26
Source title: Journal of Organizational and End User Computing (JOEUC)
Editor(s)-in-Chief: Sang-Bing Tsai (University of Electronic Science and Technology of China Zhongshan Institute, China and Research Center for Environment and Sustainable Development, Civil Aviation University of China, China)
DOI: 10.4018/JOEUC.2020040104

Purchase


Abstract

Gait is a vital biometric process for human identification in the domain of machine learning. In this article, a new method is implemented for human gait recognition based on accurate segmentation and multi-level features extraction. Four major steps are performed including: a) enhancement of motion region in frame by the implementation of linear transformation with HSI color space; b) Region of Interest (ROI) detection based on parallel implementation of optical flow and background subtraction; c) shape and geometric features extraction and parallel fusion; d) Multi-class support vector machine (MSVM) utilization for recognition. The presented approach reduces error rate and increases the CCR. Extensive experiments are done on three data sets namely CASIA-A, CASIA-B and CASIA-C which present different variations in clothing and carrying conditions. The proposed method achieved maximum recognition results of 98.6% on CASIA-A, 93.5% on CASIA-B and 97.3% on CASIA-C, respectively.

Related Content

Chi-Cheng Huang. © 2020. 22 pages.
Stoney Brooks, Xuequn Wang, Christoph Schneider. © 2020. 19 pages.
Mahmoud Zaher, Abdulaziz Shehab, Mohamed Elhoseny, Farahat Farag Farahat. © 2020. 25 pages.
Camille Grange, Henri Barki. © 2020. 22 pages.
Muhammad Sharif, Muhammad Attique, Muhammad Zeeshan Tahir, Mussarat Yasmim, Tanzila Saba, Urcun John Tanik. © 2020. 26 pages.
Sheng-Feng Sung, Pei-Ju Lee, Cheng-Yang Hsieh, Wan-Lun Zheng. © 2020. 16 pages.
Ahmad Karim, Victor Chang, Ahmad Firdaus. © 2020. 18 pages.
Body Bottom