计算机科学 ›› 2016, Vol. 43 ›› Issue (Z11): 247-251.doi: 10.11896/j.issn.1002-137X.2016.11A.057

• 模式识别与图像处理 • 上一篇    下一篇

局部特征与全局特征结合的HMM静态手势识别

张立志,黄菊,孙华东,赵志杰,陈丽,邢宗新   

  1. 哈尔滨商业大学计算机与信息工程学院 哈尔滨150028,哈尔滨商业大学计算机与信息工程学院 哈尔滨150028,哈尔滨商业大学计算机与信息工程学院 哈尔滨150028,哈尔滨商业大学计算机与信息工程学院 哈尔滨150028,哈尔滨商业大学计算机与信息工程学院 哈尔滨150028,哈尔滨商业大学科研处 哈尔滨150028
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受黑龙江省自然科学基金(F201245)资助

HMM Static Gesture Recognition Algorithm Based on Fusing Local Feature and Global Feature

ZHANG Li-zhi, HUANG Ju, SUN Hua-dong, ZHAO Zhi-jie, CHEN Li and XING Zong-xin   

  • Online:2018-12-01 Published:2018-12-01

摘要: 针对静态手势识别问题,提出了一种综合考虑局部形状与全局轮廓的隐马尔科夫模型(HMM)静态手势识别算法。该算法提取局部形状熵特征与上层轮廓特征分别作为训练数据训练每类手势的HMM参数。测试时,先凭借局部形状熵特征得出初步识别结果,然后根据初步识别结果的模糊性,附加与局部特征互补的上层轮廓特征进行再识别,得出最终识别结果。实验结果表明,该算法对于形状差异占主导地位的手势库有很好的效果,并且将静态手势的空间序列模拟成时间序列使得静态手势识别具有空间尺度不变性;同时该算法合理控制特征维数,一定程度上弱化了HMM训练时间长的弊端,加快了识别的速度。

关键词: 静态手势识别,HMM,形状熵特征,上层轮廓特征

Abstract: Focusing on the issue of static gesture recognition, a hidden markov model (HMM) static gesture recognition algorithm based on local and global contour shape was proposed.It extracts local features and upper contour shape entropy as training data of each type of gesture respectively to train its HMM parameters.While testing,the algorithm works with local shape entropy to obtain preliminary identification results,and then according to the fuzziness of prelimi-nary identification,chooses whether it needs to work with upper contour feature,which is a kind of global characteristic,and complementary to the local characteristic to get the final result.The experimental results show that the algorithm has a good effect for gesture library in which shape difference is dominant.And the ideal simulating static spatial feature data into time series makes static gesture recognition have the space scale invariance.At the same time,reasonable data dimension has shortened the training time,and accelerated the speed of recognition.

Key words: Static gesture recognition,HMM,Shape entropy,Upper contour feature

[1] Ren Z,Yuan J,Zhang Z.Robust Hand Gesture RecognitionBased on Finger-Earth Mover’s Distance with Commodity Depth Camera [J].IEEE Trans.Multimedia,2013,5(5):1110-1120
[2] Singh M,Mandal M,Basu A.Visual gesture recognition forground air traffic control using the radon transform [C]∥International Conference on Intelligent Robots and Systems .2005:2586-2591
[3] Yu C,Wang X,Huang H,et al.Vision-Based Hand GestureRecognition Using Combinational Features [C]∥Proc.of 6th Int.Conf.on Intelligent Information Hiding and Multimedia Signal Processing.2010:543-546
[4] Dardas N H,Georganas N D.Real-time Hand Gesture Detection and Recognition using Bag-of-Features and Support Vector Machine Techniques [J].IEEE Trans.on Instrumentation and Measurement,2011,60(11):3592-3607
[5] Bui T T T,Phan N H,Spitsyn V G.Face and Hand GestureRecognition Algorithm Based on Wavelet transforms and Principal Component Analysis [C]∥Proc.of 7th Int.Conf.on Strategic Technology.2012:1-4
[6] Grobel K,Assam M.Isolated sign language recognition usinghidden Markov models[C]∥Proceedings of the IEEE International Conference on Systems,Man and Cybernetics.1997:162-167
[7] 许杏.基于隐马尔可夫模型的手势识别研究[D].华南理工大学,2011
[8] 曾俊.图像边缘检测技术及其应用研究[D].武汉:华中科技大学,2011
[9] 何爱玲,王力加,郭晶鑫,等.二维图形复杂度计算与叶片轮廓复杂性分析[J].数学计算(中文版),2014,2(3):89-95
[10] 章毓晋.图像分析(第三版)[M].北京:清华大学出版社,2012:160-161
[11] Jurafsky D,Martin J H.Speech and language processing(2ed Edition)[M].Prentice Hall,2008
[12] Rabiner L R.A tutorial on hidden markov models and selected applications in speech recognition [C]∥Proceedings of the IEEE.1989:257-286
[13] Fink G A.Markov Models for Pattern Recognition(2ed Edition)[M].Springer,2007
[14] Mantyla V M.Discrete Hidden Markov Models with Application to Isolated User-Dependent Hand Gesture Recognition[R].VTT Publications,2001

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!