Two viewpoints based real-time recognition for hand gestures

作     者：Kumar, Amit Krishan Kumar, Abhishek Kaushal Guo, Shuli 

作者机构：Beijing Inst Technol Sch Automat Key Lab Complex Syst Intelligent Control & Decis Beijing Peoples R China Univ South Pacific Sch Engn & Phys Laucala Fiji 

出 版 物：《IET IMAGE PROCESSING》 (IET影像处理)

年 卷 期：2020年第14卷第17期

页      面：4606-4613页

核心收录：

学科分类：0808[工学-电气工程] 1002[医学-临床医学] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：image classification feature extraction learning (artificial intelligence) cameras geometry gesture recognition decision trees computation time hand gesture recognition single viewpoint set-up image processing feature extraction three-dimensional view single camera system geometrical features 3D view estimation classification accuracy recognition rate single-camera system real-time recognition 

摘      要：It is extremely challenging to accomplish excellent accuracy for gesture recognition using an approach where complexity in computation time for recognition is less. This study compares accuracy in hand gesture recognition of a single viewpoint set-up with proposed two viewpoint set-up for different classification techniques. The efficacy of the presented approach is verified practically with various image processing, feature extraction and classification techniques. Two camera system make geometry learning and three-dimensional (3D) view feasible compared to a single camera system. Geometrical features from additional viewpoint contribute to 3D view estimation of the hand gesture. It also improves the classification accuracy. Experimental results demonstrate that the proposed method show escalation in recognition rate compared to the single-camera system, and also has great performance using simple classifiers like the nearest neighbour and decision tree. Classification within 1 s is considered as real-time in this study.