首页 > 论文 > 激光与光电子学进展 > 53卷 > 6期(pp:61001--1)


Gesture Recognition Method of Hand over Face Occlusion in Color and Depth Images

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文


手脸近距遮挡属于深度传感器应用中具有代表性的难点问题,针对该问题提出了一种综合利用颜色与深度信息的手势识别方法。采用核模糊C-均值聚类,对手脸遮挡图像进行粗分割和灰度增强,实现手脸分离。引入初始化水平集函数,解决聚类方法导致的手势区域像元缺失问题。利用基于深度信息的梯度方向直方图(HOG) 特征对手势进行分类识别。通过采集不同人体手脸近距遮挡情形下的多种手势图像建立了样本数据库,进行了对比实验,实验结果验证了该方法的可行性和有效性。本文方法能有效分离近距遮挡的手和脸,提取得到相对完整的手势信息,深度HOG特征能够对手势空间信息进行精确描述,具有比传统形状特征更准确的识别效果。


Hand over face occlusion is a typical difficulty during depth sensor application. Aiming at this point, a gesture recognition algorithm is proposed using color and depth information comprehensively. Kernel fuzzy C-means algorithm is used to get rough segments of hand over face occlusion image and gray enhancement. The hand face separation is achieved. The initial level set function is introduced to solve the clustering method of gesture area pixels missing problem. The classification of gestures is carried based on the histogram of oriented gradient (HOG) features of depth map. The sample database is established by collecting different human hand and face close covered case gesture images. Comparative result proves the feasibility and effectiveness of the proposed algorithm. The proposed method can separate hand from face efficiently and get relatively ideal result, and the HOG features can describe the spatial information more precisely and get higher recognition rate compared with traditional characteristics.









作者单位    点击查看

刘斌:燕山大学测试计量技术与仪器重点实验室, 河北 秦皇岛 066004
赵兴:燕山大学测试计量技术与仪器重点实验室, 河北 秦皇岛 066004
胡春海:燕山大学测试计量技术与仪器重点实验室, 河北 秦皇岛 066004
万欣:燕山大学测试计量技术与仪器重点实验室, 河北 秦皇岛 066004



【1】Jalilian B, Chalechale A. Face and hand shape segmentation using statistical skin detection for sign language recognition[J].Computer Science and Information Technology, 2013, 1(3): 196-201.

【2】Wang W, Pan J. Hand segmentation using skin color and background information[C]. International Conference on Machine Learning and Cybernetics (ICMLC), 2012, 4: 1487-1492.

【3】Yaming W, Jiansheng C, Guangda S U. Efficient hand segmentation and fingertip detection using color features of skin and fingernail[J]. Ieice Transactions on Information and Systems, 2013, 96(8): 1894-1897.

【4】Gonzalez M, Collet C, Rémi D. Head tracking and hand segmentation during hand over face occlusion in sign language[C]. Proceedings of the 11th European Conference on Trends and Topics in Computer Vision, 2012:234-243.

【5】Chen Xiaolei, Zhang Aihua, Lin Dongmei, et al.. Hand detection algorithm during hand over face occlusion in sign language video[J]. Journal of Sichuan University: Engineering Science Deition, 2014, 46(2): 66-71.
陈晓雷, 张爱华, 林冬梅, 等. 适应手脸遮挡手语视频的手势检测算法[J]. 四川大学学报: 工程科学版, 2014, 46(2): 66-71.

【6】Pham N Q, Le H S, Nguyen D D, et al.. A study of feature combination in gesture recognition with kinect[M]. Berlin: Springer, 2015, 326: 459-471.

【7】Xu Pengfei, Zhang Hongying. Hand gesture segmentation and fingertip detection based on depth image of the Kinect[J]. Journal of Southwest University of Science & Technology, 2014, 29(1): 49-54.
徐鹏飞, 张红英. 基于 Kinect 深度图像信息的手势分割和指尖检测算法[J]. 西南科技大学学报, 2014, 29(1): 49-54.

【8】Yang Xiukun, Zhong Mingliang, Jing Xiaojun, et al.. Near-infrared microscopic image segmentation based on W2DPCA-FCM[J]. Acta Optica Sinica, 2013, 33(8): 0811002.
杨秀坤, 钟明亮, 景晓军,等. 基于W2DPCA-FCM的近红外显微图像分割[J]. 光学学报, 2013, 33(8): 0811002.

【9】Jeph A, Rhee F C H. Interval type-2 fuzzy C-means using multiple kernels[C]. IEEE International Conference on Fuzzy Systems, 2013, 446: 1-8.

【10】Karthika M, James A. A proposed method for document image binarization based on bit plane slicing[C]. International Conference on Advances in Engineering and Technology Research, 2014: 1-5.

【11】Li C M, Huang R, Ding Z H, et al.. A Level set method for image segmentation in the presence of intensity inhomogeneities with application to MRI[J]. IEEE Transactions on Image Process, 2011, 20(7): 2007-2016.

【12】Liu Shuping, Liu Yu, Yu Jun, et al.. Hierarchical static hand gesture recognition by combining finger detection and HOG features[J]. Journal of Image and Graphics, 2015, 20(6):781-788.
刘淑萍, 刘羽, 於俊, 等. 结合手指检测和HOG特征的分层静态手势识别[J]. 中国图象图形学报, 2015, 20(6): 781-788.

【13】Guo Pengyu, Su Ang, Zhang Hongliang, et al.. Online mixture of random naive bayes tracker combined texture with shape feature[J]. Acta Optica Sinica, 2015, 35(3): 0315002.
郭鹏宇, 苏昂, 张红良, 等. 结合纹理和形状特征的在线混合随机朴素贝叶斯视觉跟踪器[J]. 光学学报, 2015, 35(3): 0315002.

【14】Wu Yiquan, Zhou Yang, Long Yunlin. Small target detection in Hyperspectral remote sensing image based on adaptive parameter SVM[J]. Acta Optica Sinica, 2015, 35(9): 0928001.
吴一全, 周杨, 龙云淋. 基于自适应参数支持向量机的高光谱遥感图像小目标检测[J]. 光学学报, 2015, 35(9): 0928001.

【15】Sun Tao, Wang Canjin, Wang Rui, et al.. Contour bag of features applied in laser active lighting recognition system[J]. Chinese J Lasers, 2015, 42(1): 0109002.
孙涛, 王灿进, 王锐, 等. 轮廓特征包在激光主动照明识别系统中的应用[J]. 中国激光, 2015, 42(1): 0109002.


Liu Bin,Zhao Xing,Hu Chunhai,Wan Xin. Gesture Recognition Method of Hand over Face Occlusion in Color and Depth Images[J]. Laser & Optoelectronics Progress, 2016, 53(6): 061001

刘斌,赵兴,胡春海,万欣. 面向颜色深度图像手脸近距遮挡的手势识别[J]. 激光与光电子学进展, 2016, 53(6): 061001


【1】王琳琳,刘敬浩,付晓梅. 融合局部特征与深度置信网络的人脸表情识别. 激光与光电子学进展, 2018, 55(1): 11002--1

【2】鲍志强,吕辰刚. 基于Kinect的实时手势识别. 激光与光电子学进展, 2018, 55(3): 31008--1

【3】许鹏飞,姜兆亮,赵阳,朱先萌. 无色差光滑曲面特征点的提取及匹配算法. 光学学报, 2018, 38(4): 415002--1

【4】王民,李泽洋,王纯,石新源. 基于压缩感知与SURF特征的手语关键帧提取算法. 激光与光电子学进展, 2018, 55(5): 51013--1

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF