Position-Free Hand Gesture Recognition Using Single Shot MultiBox Detector Based Neural Network
Jingwei Tang, Xingtian Yao, Xin Kang, Shun Nishide, Fuji Ren · 2019
Hand Gesture Recognition plays an important role in noncontact human computer interaction. The traditional Recognition based on vision has specific requirements for the target location and equipment. We employ monocular camera to build a system which can detect the hand in any position of the screen and recognize the hand gesture. Single Shot MultiBox Detector (SSD) locates the hand position and Convolutional Neural Network (CNN) makes classification of the hand gestures. The gesture recognition performance of the proposed technique is 95.05% on Massey University gesture dataset, using CNN classifier.