School of Mechatronics Engineering, 74623Henan University of Science and Technology, China.
Collaborative Innovation Center of Machinery Equipment Advanced Manufacturing of Henan Province, China.
Sci Prog. 2022 Jan-Mar;105(1):368504221086362. doi: 10.1177/00368504221086362.
Considering that the distinctions among static hand gestures are the difference between fingers sticking out, a method of grouping and classifying hand gestures step by step by using the information of the quantity, direction, position and shape of the outstretched fingers was proposed this paper. Firstly, the gesture region was segmented by using the skin color information of the hand, and the gesture direction was normalized by using the direction information of the gesture contour lines. Secondly, the finger was segmented one by one by using convex decomposition in the hand gesture image based on the convex characteristic of the gesture shape. Thirdly, the features of quantity, direction, position and shape of the segmented fingers were extracted. Lastly, a hierarchical decision classifier embedded with deep sparse autoencoders was constructed. The quantity of fingers was used to divide the gesture images into groups first, then the direction, position and shape features of the fingers were used to subdivide and recognize gestures within each group. The experimental results show that the proposed method is robust as lighting, direction and scale changes and significantly superior to the traditional method both in the recognition rate and the recognition stability.
考虑到手的静态手势之间的区别在于伸出的手指，本文提出了一种使用伸出手指的数量、方向、位置和形状信息对手势进行分组和分类的方法。首先，通过使用手部的肤色信息对手势区域进行分割，并通过手势轮廓线的方向信息对手势方向进行归一化。其次，基于手势形状的凸性特征，在基于手势图像中使用凸分解对手指进行逐个分割。第三，提取分割手指的数量、方向、位置和形状特征。最后，构建了一个嵌入深度稀疏自动编码器的分层决策分类器。首先使用手指的数量将手势图像分为组，然后使用手指的方向、位置和形状特征对手势进行细分和识别。实验结果表明，该方法对光照、方向和尺度变化具有鲁棒性，在识别率和识别稳定性方面明显优于传统方法。
