基于曲率局部二值模式的深度图像手势特征提取

doi:10.11772/j.issn.1001-9081.2016.10.2885

计算机应用 ›› 2016, Vol. 36 ›› Issue (10): 2885-2889.DOI: 10.11772/j.issn.1001-9081.2016.10.2885

基于曲率局部二值模式的深度图像手势特征提取

尚常军, 丁瑞

首都师范大学信息工程学院, 北京 100048

收稿日期:2016-04-05 修回日期:2016-06-14 发布日期:2016-10-10
通讯作者: 尚常军,E-mail:wayl@163.com
作者简介:尚常军(1990—),男,山东莱芜人,硕士研究生,主要研究方向:模式识别、数字图像处理;丁瑞(1978—),男,安徽池州人,讲师,博士,主要研究方向:计算机视觉、智能控制。

Gesture feature extraction of depth image based on curvature and local binary pattern

SHANG Changjun, DING Rui

College of Information Engineering, Capital Normal University, Beijing 100048, China

Received:2016-04-05 Revised:2016-06-14 Published:2016-10-10

摘要/Abstract

摘要： 针对复杂环境下的深度图像手势特征提取信息冗余量大、编码不稳定等问题，提出了一种改进的基于曲率局部二值模式（LBP）的深度图像手势特征提取算法。该算法首先通过坐标转换将分割出的手势深度数据转换为点云数据；其次利用移动最小二乘法对手势点云数据进行曲面拟合；然后计算出能够更加准确描述物体三维表面几何信息特征的高斯曲率；最后利用改进的LBP均匀模式对高斯曲率数据进行编码形成特征向量。在美国手语（ASL）手势数据库上该算法的平均识别率达到了92.1%，与3D局部二值模式（3DLBP）和梯度LBP相比分别提高了18.5个百分点和13.7个百分点。实验结果表明，该算法可以区分外部轮廓相似但内部结构不同的手势，有效提高了在描述手势深度图像内部细节方面的准确性。

关键词: 手势识别, 深度图像, 高斯曲率, 局部二值模式, 特征提取

Abstract: Focusing on the information redundancy and encoding instability of depth image for gesture feature extraction in complex environment, an improved gesture feature extraction algorithm for depth image based on curvature-LBP (Local Binary Pattern) was proposed. Firstly, the divided gesture depth data to the point cloud data was converted through the coordinate conversion. Secondly, surface fitting was fulfilled with the moving least square method. And then the Gaussian curvature was calculated to describe the characteristics of the 3D surface geometry more accurately. Finally, the improved LBP uniform model was applied to encode the Gaussian curvature data and form a feature vector. In the American Sign Language (ASL) database, the average recognition rate of the proposed algorithm reached 91.20%, which 18.5 percentage points and 13.7 percentage points higher than 3DLBP and gradient LBP. Simulation results show that the proposed algorithm can recognize the gestures with similar outline and different shape, and improve the precision of describing the internal details in gesture depth image.

Key words: gesture recognition, depth image, Gaussian curvature, Local Binary Pattern (LBP), feature extraction

中图分类号:

TP391.41

尚常军, 丁瑞. 基于曲率局部二值模式的深度图像手势特征提取[J]. 计算机应用, 2016, 36(10): 2885-2889.

SHANG Changjun, DING Rui. Gesture feature extraction of depth image based on curvature and local binary pattern[J]. Journal of Computer Applications, 2016, 36(10): 2885-2889.

参考文献

[1] JIA H, WANG L, SUN Y, et al. Color face recognition based on color space normalization and quaternion matrix representation [C]//ICDH 2012: Proceedings of the 4th International Conference on Digital Home. Piscataway, NJ: IEEE, 2012: 133-137.
[2] EROL A, BEBIS G, NICOLESCU M, et al. Vision-based hand pose estimation: a review [J]. Computer Vision and Image Understanding, 2007, 208(1/2): 52-73.
[3] KOUTIDOU M, GRAUWET T, AVHARYA P. Effect of different combined mechanical and thermal treatments on the volatile fingerprint of a mixed tomato-carrot system [J]. Journal of Food Engineering, 2016, 168: 137-147.
[4] TAKANO H, MURAKAMI M, NAKAMURA K. Iris recognition by rotation spreading neural network [C]//Proceedings of the 2004 IEEE International Conference on Neural Networks. Piscataway, NJ: IEEE, 2004: 2589-2594.
[5] WACHS J P, KOLSCH M, STRERN H, et al. Vision-based hand gesture applications [J]. Communications of the ACM, 2011, 54(2): 60-71.
[6] LI Y. Hand gesture recognition using Kinect [C]//ICSESS 2012: Proceedings of the 2012 IEEE 3rd International Conference on Software Engineering and Service Science. Piscataway, NJ: IEEE, 2012: 196-199.
[7] SILANON K, SUVONVORN N. Hand motion analysis for Thai alphabet recognition using HMM [J]. International Journal of Information and Electronics Engineering, 2011, 1(1): 65-71.
[8] 曹雏清, 李瑞峰, 赵立军. 基于深度图像技术的手势识别方法[J]. 计算机工程, 2012, 38(8):16-2.(CAO C Q, LI R F, ZHAO L J. Hand posture recognition method based on depth image technology [J]. Computer Engineering, 2012, 38(8): 16-21.)
[9] 王松林, 徐文胜. 基于Kinect深度信息与骨骼信息的手指指尖识别方法[J]. 计算机工程与应用, 2016, 52(3): 169-173.(WANG S L, XU W S. Fingertips recognition based on Kinect depth and skeleton data [J]. Computer Engineering and Applications, 2016, 52(3): 169-173.)
[10] HUANG D, HU W, CHANG S. Vision-based hand gesture recognition using PCA+Gabor filters and SVM [C]//Proceedings of the 5th International Conference on Information Hiding and Multimedia Signal Processing. Piscataway, NJ: IEEE, 2009: 1-4.
[11] SHAO Z, BIN Y, WEI W. Feature learning based on SAE-PCA network for human gesture recognition in RGBD images [J]. Neurocomputing, 2015, 151: 565-573.
[12] 韩强. 基于普通摄像头的人体几何尺寸测量系统[D]. 天津:天津大学, 2012: 25-27.(HAN Q. The human geometrical dimensions measuring system based on ordinary camera[D]. Tianjin: Tianjin University, 2012: 25-27.)
[13] DING Y. Static hand-gesture recognition using HOG and improved LBP features [J]. International Journal of Digital Content Technology and its Applications, 2011, 5(11): 236-243.
[14] OJALA T, PIETIKAINEN M, HARWOODD. A comparative study of texture measures with classification based on feature distributions [J]. Pattern Recognition, 1996, 29(1): 51-59.
[15] ZHANG K, SONG H, ZHANG L. Active contours driven by local image fitting energy [J]. Pattern Recognition, 2010, 43(4): 1199-1206.
[16] 李晓丽, 李小红. 梯度-LBP优化深度图像分析的性别人脸识别[J]. 计算机应用研究, 2014, 31(11): 3502-3505.(LI X L, LI X H. Depth image analysis optimized by gradient-LBP for gender face recognition [J]. Application Research of Computers, 2014, 31(11): 3502-3505.)
[17] OTSU N. Threshold selection method from gray-level histogram [J]. IEEE Transactions on Systems, Man and Cybernetics, 1979, 9(1): 62-64.
[18] 肖超云, 朱兴伟. 基于Ostu准则即图像熵的阈值分割算法[J]. 计算机工程, 2007, 33(14): 188-189.(XIAO C Y, ZHU X W. Threshold selection algorithm for image segmentation based on Otsu rule and image entropy [J]. Computer Engineering, 2007, 33(14): 188-189.)

基于曲率局部二值模式的深度图像手势特征提取

Gesture feature extraction of depth image based on curvature and local binary pattern

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]	郑志强, 胡鑫, 翁智, 王雨禾, 程曦. 基于改进DenseNet的牛眼图像特征提取方法[J]. 计算机应用, 2021, 41(9): 2780-2784.
[2]	佘玉龙, 张晓龙, 程若勤, 邓春华. 基于边缘关注模型的语义分割方法[J]. 计算机应用, 2021, 41(2): 343-349.
[3]	赵津, 宋文爱, 邰隽, 杨吉江, 王青, 李晓丹, 雷毅, 邱悦. 儿童阻塞性睡眠呼吸暂停计算机人脸辅助诊断综述[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3394-3401.
[4]	朱新成, 何坤金, 倪娜, 郝博. 基于改进迭代最近点算法的接骨板贴合性快捷计算方法[J]. 计算机应用, 2021, 41(10): 3033-3039.
[5]	尹春勇, 何苗. 基于改进胶囊网络的文本分类[J]. 计算机应用, 2020, 40(9): 2525-2530.
[6]	周云, 陈淑荣. 基于双流非局部残差网络的行为识别方法[J]. 计算机应用, 2020, 40(8): 2236-2240.
[7]	张豪, 张强, 邵思羽, 丁海斌. 深度学习在单图像三维模型重建的应用[J]. 计算机应用, 2020, 40(8): 2351-2357.
[8]	张家岗, 李达平, 杨晓东, 邹茂扬, 吴锡, 胡金蓉. 基于深度卷积特征光流的形变医学图像配准算法[J]. 计算机应用, 2020, 40(6): 1799-1805.
[9]	徐代, 岳璋, 杨文霞, 任潇. 基于改进的三向流Faster R-CNN的篡改图像识别[J]. 计算机应用, 2020, 40(5): 1315-1321.
[10]	郭志强, 胡永武, 刘鹏, 杨杰. 基于特征融合的室外天气图像分类[J]. 计算机应用, 2020, 40(4): 1023-1029.
[11]	张俊升, 徐晶晶, 余伟. 面部美化图像质量无参考评价方法[J]. 计算机应用, 2020, 40(4): 1184-1190.
[12]	刘尚旺, 刘承伟, 张爱丽. 基于深度可分卷积神经网络的实时人脸表情和性别分类[J]. 计算机应用, 2020, 40(4): 990-995.
[13]	沈亮, 王鑫, 陈曙晖. 面向移动应用识别的结构化特征提取方法[J]. 计算机应用, 2020, 40(4): 1109-1114.
[14]	朱喆, 许少华. 降噪自编码器深度卷积过程神经网络及在时变信号分类中的应用[J]. 计算机应用, 2020, 40(3): 698-703.
[15]	陈梅婕, 谢振平, 陈晓琪, 许鹏. 专利新词发现的双向聚合度特征提取新方法[J]. 计算机应用, 2020, 40(3): 631-637.