结合手势二进制编码和类-Hausdorff距离的手势识别

doi:10.3969/j.issn.0372-2112.2017.09.032

电子学报 ›› 2017, Vol. 45 ›› Issue (9): 2281-2291.DOI: 10.3969/j.issn.0372-2112.2017.09.032

结合手势二进制编码和类-Hausdorff距离的手势识别

冯志全^1,2, 杨学文^1,2, 徐涛^1,2, 刘弘³, 吕娜^1,2, 杨晓辉^1,2, 徐治鹏^1,2

1. 济南大学信息科学与工程学院, 山东济南 250022;
2. 山东省网络环境智能计算技术重点实验室, 山东济南 250022;
3. 山东省分布式计算机软件新技术重点实验室, 山东济南 250014

收稿日期:2015-02-04 修回日期:2015-11-13 出版日期:2017-09-25
- 作者简介:
- 冯志全,男,1964年出生,博士,教授,硕士生导师,CCF会员,主要研究方向为人机交互、虚拟现实、图像处理.E-mail:ise_fengzq@ujn.edu.cn;杨学文,男,1988年出生,硕士研究生,主要研究方向为人机交互、虚拟现实.E-mail:515031162@qq.com;吕娜,女,1979年生,博士,讲师,主要研究方向为人机交互;杨晓辉,男,1985年生,博士,讲师,主要研究方向为人机交互;徐治鹏,男,1989年生,硕士研究生,主要研究方向为人机交互.
- 基金资助:
- 国家自然科学基金项目 (No.61472163，No.61603151）; 国家重点研发计划项目 (No.2016YFB1001403）; 山东省重点研发计划项目 (No.2015GGX101025）; 济南大学博士科研基金 (No.XBS1534）

Gesture Recognition Based on Combining Gesture Binary Descriptor and Hausdorff-Like Distance

FENG Zhi-quan^1,2, YANG Xue-wen^1,2, XU Tao^1,2, LIU Hong³, LÜ Na^1,2, YANG Xiao-hui^1,2, XU Zhi-peng^1,2

1. School of Information Science and Engineering, University of Jinan, Jinan, Shandong 250022, China;
2. Shandong Provincial Key Laboratory of Network Based Intelligent Computing, Jinan, Shandong 250022, China;
3. Shandong Provincial Key Laboratory for Novel Distributed Computer Softwave Technology, Jinan, Shandong 250014, China

Received:2015-02-04 Revised:2015-11-13 Online:2017-09-25 Published:2017-09-25
- Supported by:
- National Natural Science Foundation of China (No.61472163, No.61603151); Program of National Key Research and Development Program of China国家重点研发计划 National Key Research and Development Program of China (No.2016YFB1001403); Key Research and Development Project of Shandong Provicne (No.2015GGX101025); Doctoral Science Research Foundation of Jinan University (No.XBS1534)

摘要/Abstract

摘要： 针对目前动态手势识别方法受手势旋转、平移、缩放的影响，并解决手势识别的实时性问题，提出一种基于手势二进制编码和类-Hausdorff距离模板匹配的手势识别方法.首先，把分割好的手势图像进行标准化处理，求出标准化图像中的手势主方向，建立二维手势直角坐标系，提取空间手势特征；其次，根据前五帧手势图像中手势像素点个数的变化量识别出动态手势类型；然后，用手势二进制描述子从动态手势类型中再筛选出可能的候选手势集合；最后，用类-Hausdorff距离模板匹配方法从候选手势集合中识别出最终手势.主要创新点在于：提出的动态手势类型识别和手势二进制描述子匹配的方法，大大缩短了动态手势识别的时间；提出的结合手势主方向的类-Hausdorff距离方法，不仅对旋转、平移和缩放手势具有不变性，而且对区分度较小的手势也具有较高的识别准确率.实验结果表明，在光照相对稳定的条件下，该方法能够实时准确的实现动态手势识别，总体识别率达到95%以上，对发生缩放的手势识别率能达到92%以上，对发生旋转的手势识别率能达到87%以上.本文算法已经在一个基于手势的人机交互界面中得到应用.

关键词: 动态手势识别, 手势主方向, 动态手势类型识别, 手势二进制描述子, 类-Hausdorff距离

Abstract: Since the dynamic gesture recognition algorithm is influenced by rotation,translation and scaling,and real-time gesture recognition is still a challenging issue,we propose a dynamic gesture recognition algorithm which is based on the combination of gesture binary descriptor and Hausdorff-like distance template matching.Firstly,we converted the segmented gesture image to the standardized image,then calculated the main direction of gesture in the image,and built a 2D rectangular coordinate system to extract the gesture features.Secondly,the specific dynamic gesture type can be identified according to changes in the amount of gesture pixel points from the top five frames.Next,we used gesture binary descriptor to select a part of gesture from the specific dynamic gesture type.Finally,the method of Hausdorff-like distance template matching is used to recognize the final gesture.The main innovation of this paper embodies in two aspects.Firstly,the dynamic gesture type recognition and the method of gestures binary descriptor matching proposed in this paper greatly shorten the time cost of dynamic gesture recognition.Secondly,Hausdorff-like distance method with the main direction of gesture not only has the in-variance on rotation,translation and scaling gestures,but also has a higher recognition rate on smaller gestures.Experimental results show that this algorithm can achieve real-time correct recognition of gestures in relatively stable light conditions.The overall recognition rate can reach 95%,the recognition rate of scal-ing gestures is more than 92% and the recognition rate of rotation gestures is more than 87%.This algorithm has been applied in a human-computer interface system based on hand gesture.

Key words: dynamic gesture recognition, the main direction of gesture, dynamic gesture type recognition, gesture binary descriptor, Hausdorff-like distance

中图分类号:

TP391

. 结合手势二进制编码和类-Hausdorff距离的手势识别[J]. 电子学报, 2017, 45(9): 2281-2291.

. Gesture Recognition Based on Combining Gesture Binary Descriptor and Hausdorff-Like Distance[J]. Acta Electronica Sinica, 2017, 45(9): 2281-2291.

参考文献

[1] 冯志全,杨波,徐涛,唐好魁,吕娜.基于自然手势跟踪的直接操作型三维人机交互范式[J].计算机学报,2014,37(6):1309-1323. Feng Zhi-Quan,Yang Bo,Xu Tao,Tang Hao-Kui,LÜ Na.3D direct human-computer interface paradigm based on free hand tracking[J].Chinese Journal of Computers,2014,37(6):1309-1323.(in Chinese)
[2] 冯志全,杨波,郑艳伟,徐涛,唐好魁.基于用户行为分析的手势跟踪方法[J].软件学报,2013,24(9):2101-2116. Feng Zhi-Quan,Yang Bo,Zheng Yan-Wei,Xu Tao,Tang Hao-Kui.Hand tracking based on behavioral analysis for users[J].Journal of Software,2013,24(9):2101-2116.(in Chinese)
[3] 任海兵,祝远新,徐光祐,林学訚,张哓平.基于视觉手势识别的研究-综述[J].电子学报,2000,28(2):118-121. Ren Hai-Bing,Zhu Yuan-Xin,Xu Guang-You,Lin Xue-Yin,Zhang Xiao-Ping.Vision-based recognition of hand gestures:a survey[J].Acta Electronica Sinica,2000,28(2):118-121.(in Chinese)
[4] 关然,徐向民,罗雅愉,苗捷,裘索.基于计算机视觉的手势检测识别技术[J].计算机应用与软件,2013,30(1):155-164. Gu Ran,Xu Xiang-Min,Luo Ya-Yu,Miao Jie,Qiu Suo.Detection and recognition technology of computer vision based gesture[J].Computer Applications and Software,2013,30(1):155-164.(in Chinese)
[5] 武汇岳,张凤军,刘玉进,戴国忠.基于视觉的手势界面关键技术研究[J].计算机学报,2009,32(10):2030-2041. Wu Hui-Yue,Zhang Feng-Jun,Liu Yu-Jin,Dai Guo-Zhong.Research on the key technology of vision based gesture interface[J].Chinese Journal of Computers,2009,32(10):2030-2041.(in Chinese)
[6] Suk Heung-Il,Sin Bong-Kee,Lee Seong-Whan.Hand gesture recognition based on dynamic Bayesian network framework[J].Pattern Recognition,2010,43(9):3059-3072.
[7] Mohamed B K,Francois B.Gesture recognition by learning local motion signatures[A].IEEE Conference on Computer Vision and Pattern Recognition[C].San Francisco,USA:IEEE,2010.2745-2752.
[8] 王西颖,戴国忠,张习文,张凤军.基于HMM-FNN模型的复杂动态手势识别[J].软件学报,2008,19(9):2302-2312. Wang Xi-Ying,Dai Guo-Zhong,Zhang Xi-Wen,Zhang Feng-Jun.Recognition of complex dynamic gesture based on HMM-FNN model[J].Journal of Software,2008,19(9):2302-2312.(in Chinese)
[9] 张建忠,常丹华.基于区间分布概率矩阵模型的动态手势识别方法[J].电子技术应用,2013,39(1):72-75. Zhang Jian-Zhong,Chang Dan-Hua.Dynamic gesture recognition method based on probability matrix model of interval distribution[J].Application of Electronic Technique,2013,39(1):72-75.(in Chinese)
[10] Li Y T,Wachs J P.HEGM:A hierarchical elastic graph matching for hand gesture recognition[J].Pattern Recognition,2014,47(1):80-88.
[11] Wang H,Fu J,Lu Y,et al.Depth sensor assisted real-time gesture recognition for interactive presentation[J].Journal of Visual Communication and Image Representation,2013,24(8):1458-1468.
[12] Saeed Nasri,Alireza Behrad,Farbod Razzazi.Spatio-temporal 3D surface matching for hand gesture recognition using ICP algorithm[J].Signal,Image and Video Processing,2015,9(5):1205-1220.
[13] 何力,傅忠谦,顾理.一种基于最大似然Hausdorff距离的手势识别算法.电子技术,2010,05:5-7. He Li,Fu Zhong-Qian,Gu li.Gesture recognition based on maximum likelihood Hausdorff distance[J].Electronic Technology,2010,05:5-7.(in Chinese)
[14] Huttenlocher D P,Rucklidge W J.A multi-resolution technique for comparing images using the Hausdorff distance[R].New York State,USA:Cornell University,Department of Computer Science.Ithaca,1992.
[15] 杨波,宋晓娜,冯志全,郝晓艳.复杂背景下基于空间分布特征的手势识别算法[J].计算机辅助设计与图形学学报,2010(10):1841-1848. Yang Bo,Song Xiao-Na,Feng Zhi-Quan,Hao Xiao-Yan.The gesture recognition algorithm based on space distribution features under clutter background[J].Journal of Computer-Aided Design & Computer Graphics,2010(10):1841-1848.(in Chinese)
[16] 唐好魁.基于双肤色模型的肤色分割方法的研究[D].济南:山东大学,2009. Tang Hao-Kui.Skin color segmentation method based on double skin-color model[D].Jinan:University of Shandong,2009.(in Chinese)
[17] 王颖,王爱民.一种鲁棒的二进制图像特征点描述子[J].东南大学学报(自然科学版),2012,42(2):265-269. Wang Ying,Wang Ai-Min.Robust binary feature point descriptor[J].Journal of Southeast University(Natural Science Edition),2012,42(2):265-269.(in Chinese)
[18] 张良国,吴江琴,高文,姚鸿勋.基于Hausdorff距离的手势识别[J].中国图象图形学报:A版,2002,7(11):1144-1150. Zhang Liang-Guo,Wu Jiang-Qin,Gao Wen,YAO Hong-Xun.Hand gesture recognition based on Hausdorff distance[J].Journal of Image and Graphics:A,2002,7(11):1144-1150.(in Chinese)
[19] Wang R Y,Popovic' J.Real-time hand-tracking with a color glove[J].ACM Transactions on Graphics,2009,28(3):Article No.63.

结合手势二进制编码和类-Hausdorff距离的手势识别

Gesture Recognition Based on Combining Gesture Binary Descriptor and Hausdorff-Like Distance

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	韩光洁, 赵腾飞, 刘立, 张帆, 徐政伟. 基于多元区域集划分的工业数据流概念漂移检测[J]. 电子学报, 2023, (): 1-11.
[2]	彭锦佳, 王辉兵. 基于异构卷积神经网络集成的无监督行人重识别方法[J]. 电子学报, 2023, (): 1-13.
[3]	余伶俐, 易倩, 金鸣岳, 周开军. 面向仿射目标识别的几何与仿生融合特征提取方法[J]. 电子学报, 2023, (): 1-12.
[4]	郭凯红, 崔明茜, 刘婷婷. 模糊知识测度下图像脉冲噪声去除方法[J]. 电子学报, 2023, (): 1-14.
[5]	李杨帅, 彭斐, 韩倩, 李小帅, 解光军. 一种针对QCA电路自动布局布线的混合策略研究[J]. 电子学报, 2023, 51(3): 666-674.
[6]	吕杭, 蒋明峰, 李杨, 张鞠成, 王志康. 基于混合时频域特征的卷积神经网络心律失常分类方法的研究[J]. 电子学报, 2023, 51(3): 701-711.
[7]	郑云飞, 王晓兵, 张雄伟, 曹铁勇, 孙蒙. 基于金字塔知识的自蒸馏HRNet目标分割方法[J]. 电子学报, 2023, 51(3): 746-756.
[8]	隗昊, 唐焕玲, 周爱, 张益嘉, 陈飞, 鲁明羽. 基于双路分段注意力神经张量网络的临床文本关系抽取[J]. 电子学报, 2023, 51(3): 658-665.
[9]	黄赟, 张帆, 郭威, 陈立, 羊光. 一种基于数据标准差的卷积神经网络量化方法[J]. 电子学报, 2023, 51(3): 639-647.
[10]	范兵兵, 何庭建, 张聪炫, 陈震, 黎明. 联合遮挡约束与残差补偿的特征金字塔光流计算方法[J]. 电子学报, 2023, 51(3): 648-657.
[11]	张晶, 王翌歆, 任永功. 统一全局空间表达的脑电信号跨被试情感识别[J]. 电子学报, 2023, (): 1-9.
[12]	申铉京, 李涵宇, 黄永平, 王玉. 基于自适应多尺度特征融合网络的车辆检测方法[J]. 电子学报, 2023, (): 1-9.
[13]	陈习坤, 杨俊美. 基于离散小波包变换与胶囊生成对抗网络的语音超分辨率算法[J]. 电子学报, 2023, (): 1-11.
[14]	张娜, 包梓群, 罗源, 吴彪, 涂小妹. 基于改进Cascade R-CNN算法在目标检测上的应用[J]. 电子学报, 2023, (): 1-11.
[15]	但志平, 方帅领, 孙航, 李晶, 万俊. 基于双判别器异构CycleGAN框架下多阶通道注意力校准的室外图像去雾[J]. 电子学报, 2023, (): 1-14.