• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

J4 ›› 2015, Vol. 37 ›› Issue (01): 139-145.

• 论文 • 上一篇    下一篇

基于表观特征分析的手势识别及其应用

屈燕琴,李昕,卢夏衍   

  1. (上海大学机电工程与自动化学院,上海 200072)
  • 收稿日期:2013-04-15 修回日期:2013-07-24 出版日期:2015-01-25 发布日期:2015-01-25

Hand gesture recognition based on analysis
of appearance features and its application  

QU Yanqin,LI Xin,LU Xiayan   

  1. (School of Mechatronic Engineering and Automation,Shanghai University,Shanghai 200072,China)
  • Received:2013-04-15 Revised:2013-07-24 Online:2015-01-25 Published:2015-01-25

摘要:

针对复杂背景下的手势识别容易受到环境干扰造成的识别困难问题,通过分析手势的表观特征,提出并实现了一种可用于自然人机交互的手势识别算法。该算法基于Kinect深度图像实现手势区域分割,然后提取手势手指弧度、指间弧度、手指数目等具有旋转缩放不变性的表观特征,运用最小距离法实现快速分类。并将该算法成功运用于实验室三指灵巧手平台,达到了理想的控制效果。实验表明该算法具有良好的鲁棒性,针对九种常用手势,平均识别率达到94.3%。

关键词: 计算机视觉, 深度图像, 手指弧度, 表观特征, 手势识别

Abstract:

Hand gesture recognition in complex background is susceptible to environmental interference, thus leading to recognition difficulty. According to this recognition problem, by analyzing the appearance features of hand gesture, a hand gesture recognition algorithm for natural human computer interaction is proposed and implemented. By using depth images which obtain from Kinect, we extract features like gesture finger radians, radians between fingers and the number of fingers, and properly utilize minimum distance algorithm for achieving fast and efficient classification. Experimental results show that the algorithm is robust and real-time with an average recognition rate of 94.3% for nine frequently-used gestures.

Key words: computer vision;depth image;finger radian;appearance features;gesture recognition