• •    

一种基于网格采样的手势识别算法

董立岩1,高洋2,李永丽3,任时鸣4   

  1. 1. 吉林大学计算机科学与技术学院
    2. 吉林大学 计算机科学与技术学院
    3. 东北师范大学计算机学院
    4. 北京理工大学 管理与经济学院
  • 收稿日期:2012-12-07 修回日期:2013-03-28 发布日期:2013-06-20
  • 通讯作者: 李永丽

Gesture Recognizing Algorithm Based on Grid Resample

  • Received:2012-12-07 Revised:2013-03-28 Published:2013-06-20
  • Contact: LI Yong-Li 李永丽

摘要: 为克服传统手势识别算法的缺点,提高手势识别的准确率并充分考虑人机交互因素,提出一种基于模板的手势识别算法。该算法通过对用户输入的点集合图形进行旋转、平移、放缩、采样以及模板对比等操作实现手势识别。实验结果表明,与传统识别算法相比该算法的准确率有明显提高,时间消耗有很小的增加。该算法对基于触摸屏的手势交互技术有一定的参考价值和很强的实践意义。

关键词: 手势交互, 手势识别, 基于模板识别

Abstract: In order to overcome the shortcomings of conventional gesture recognizers, improve the accuracy of recognizing and take human computer interaction factors into consideration, a new template based recognition algorithm called Grid was proposed. The algorithm processes users’ input gesture by rotating, translating, scale normalizing and resampling it. In particular, it uses a gird based method to resample the most representative points of gesture. A formal experiment showed the Grid has a higher accuracy with a tolerable larger time cost.

Key words: gesture interaction, gesture recognition, template recognition

[1] 董立岩, 高洋, 李永丽, 任时鸣. 一种基于网格采样的手势识别算法[J]. 吉林大学学报(工学版), 2013, 43(06): 1621-1625.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!