[1]董旭德,许源平,舒红平,等.基于质心分水岭算法的静态手势分割算法模型[J].智能系统学报,2019,14(2):346-354.[doi:10.11992/tis.201804028]
DONG Xude,XU Yuanping,SHU Hongping,et al.Static gesture segmentation algorithm model based on centroid watershed algorithm[J].CAAI Transactions on Intelligent Systems,2019,14(2):346-354.[doi:10.11992/tis.201804028]
点击复制
DONG Xude,XU Yuanping,SHU Hongping,et al.Static gesture segmentation algorithm model based on centroid watershed algorithm[J].CAAI Transactions on Intelligent Systems,2019,14(2):346-354.[doi:10.11992/tis.201804028]
基于质心分水岭算法的静态手势分割算法模型
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
14
期数:
2019年第2期
页码:
346-354
栏目:
学术论文—机器学习
出版日期:
2019-03-05
- Title:
- Static gesture segmentation algorithm model based on centroid watershed algorithm
- Keywords:
- skin-like background; static gesture segmentation; ICWA algorithm; wrist segmentation; gesture recognition; convexity detection; PCA dimension reduction; deep learning
- 分类号:
- TP18
- 摘要:
- 为了解决在类肤色背景下难以从图像中高效地分割出完整静态手势的问题，提出了基于质心分水岭算法（improved centroid watershed algorithm，ICWA）的静态手势分割模型。该ICWA算法可以有效地减少图像梯度对手势分割的影响并完整地提取出肤色区域。此外，本文设计了一种将PCA （principal component analysis）降维和凸性检测算法相结合的方法，可以根据对凸点准确提取手腕的割线。同时，利用卷积神经网络（convolutional neural networks，CNN）在标准数据库上进行了初步的手势自动识别实验。实验结果表明：该分割模型对于9种静态手势的平均识别率达到了97.85%。
- Abstract:
- Considering the difficulty in effectively achieving complete static gesture segmentations from skin-like background regions, this paper proposes an integrated static gesture segmentation model based on an improved centroid watershed algorithm (ICWA). The ICWA algorithm significantly reduces the interference of image gradient on gesture segmentations such that it can completely extract skin regions from images. Moreover, a novel method is designed and implemented by integrating principal component analysis (PCA) dimension reduction and convexity detection algorithms, which can accurately extract the cutting line of the wrist according to convex points. Preliminary experiments of automatic gesture recognitions based on convolutional neural network (CNN) were carried out on a benchmark database. The experimental results show that the proposed model can achieve a recognition rate of 97.85% on average for nine different static gestures.
- 参考文献/References:
-
[1] 易靖国, 程江华, 库锡树. 视觉手势识别综述[J]. 计算机科学, 2016, 43(S1):103-108 YI Jingguo, CHENG Jianghua, KU Xishu. Review of gestures recognition based on vision[J]. Computer science, 2016, 43(S1):103-108
[2] 曹昕燕, 赵继印, 李敏. 基于肤色和运动检测技术的单目视觉手势分割[J]. 湖南大学学报(自然科学版), 2011, 38(1):78-83 CAO Xinyan, ZHAO Jiyin, LI Min. Monocular vision gesture segmentation based on skin color and motion detection[J]. Journal of Hunan university (natural sciences), 2011, 38(1):78-83
[3] 张国亮, 王展妮, 王田. 应用计算机视觉的动态手势识别综述[J]. 华侨大学学报(自然科学版), 2014, 35(6):653-658 ZHANG Guoliang, WANG Zhanni, WANG Tian. Survey on dynamic hand gesture recognition with computer vision[J]. Journal of Huaqiao university (natural science), 2014, 35(6):653-658
[4] WU Ying, HUANG T S. Vision-based gesture recognition:a review[C]//International Gesture Workshop on Gesture-Based Communication in Human-Computer Interaction. Berlin, Heidelberg, Germany:Springer-Verlag, 1999:103-115.
[5] TARA R Y, PAULUS T, SANTOSA I, et al. Hand segmentation from depth image using anthropometric approach in natural interface development[J]. International journal of scientific & engineering research, 2012, 3(5):208-215.
[6] 王先军, 白国振, 杨勇明. 复杂背景下BP神经网络的手势识别方法[J]. 计算机应用与软件, 2013, 30(3):247-249 WANG Xianjun, BAI Guozheng, YANG Yongming. Hand gesture recognition based on BP neural network in complex background[J]. Computer applications and software, 2013, 30(3):247-249
[7] PATEL D G. Point pattern matching algorithm for recognition of 36 ASL gestures[J]. International journal of science and modern engineering, 2013, 7(1):24-28.
[8] LEE J Y, RHEE G W, DONG W S. Hand gesture-based tangible interactions for manipulating virtual objects in a mixed reality environment[J]. International journal of advanced manufacturing technology, 2010, 51(9/10/11/12):1069-1082.
[9] ZENG Jianchao, WANG Yue, TURNER R, et al. Vision-based finger tracking of breast palpation for improving breast self-examination[C]//Proceedings of 18th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Bridging Disciplines for Biomedicine. Amsterdam, Netherlands:IEEE, 1996:148-149.
[10] DAVIS J, SHAH M. Visual gesture recognition[J]. IEE proceedings-vision, image and signal processing, 1994, 141(2):101-106.
[11] DORFMULLER-ULHAAS K, SCHMALSTIEG D. Finger tracking for interaction in augmented environments[C]//Proceedings. IEEE and ACM International Symposium on Augmented Reality. New York, NY, USA:IEEE, 2001:55-64.
[12] 张国家, 左敦稳, 黎向锋, 等. 基于圆形梯度的手势分割算法的设计与实现[J]. 机械设计与制造工程, 2013, 42(9):1-6 ZHANG Guojia, ZUO Dunwen, LI Xiangfeng, et al. Design and development of a new gesture segmentation algorithm based on circular gradient[J]. Machine design and manufacturing engineering, 2013, 42(9):1-6
[13] 杨磊, 隋云衡, 姚立虎. 结合肤色分割与手形匹配算法的静态手势检测[J]. 信息通信, 2013(4):4-6 YANG Lei, SUI Yunheng, YAO Lihu. The static gesture detection with combining skin color segmentation and hand-shape matching algorithm[J]. Information and communication, 2013(4):4-6
[14] 张羽, 徐端全. OpenCV分水岭算法的改进及其在细胞分割中的应用[J]. 计算机应用, 2012, 32(S1):134-136 ZHANG Yu, XU Duanquan. Improvement on watershed algorithm of OpenCV and its application in cell image segmentation[J]. Journal of computer applications, 2012, 32(S1):134-136
[15] 胡学敏, 沈朝晓, 王司雨, 等. 基于多边形凹凸点检测的远距离手势识别[J]. 信息通信, 2015(9):57-58 HU Xueming, SHEN Chaoxiao, WANG Siyu, et al. Remote gesture recognition based on polygon bump pointdetection[J]. Information and communication, 2015(9):57-58
[16] 邱瑞, 祝日星, 许宏科. 基于改进分水岭算法的图像分割算法[J]. 吉林大学学报(理学版), 2017, 55(3):629-634 QIU Rui, ZHU Rixing, XU Hongke. Image segmentation algorithm based on improved watershed algorithm[J]. Journal of Jilin university (science edition), 2017, 55(3):629-634
[17] 王晓, 踪琳. 基于OpenCV视觉库的嵌入式视频处理系统[J]. 电子质量, 2017(3):54-59 WANG Xiao, ZONG Lin. Embedded video monitoring system based on OpenCV visual library[J]. Electronics quality, 2017(3):54-59
[18] PRIYAL S P, BORA P K. A robust static hand gesture recognition system using geometry based normalizations and Krawtchouk moments[J]. Pattern recognition, 2013, 46(8):2202-2219.
备注/Memo
收稿日期:2018-04-18。
基金项目:国家自然科学基金项目（61203172）；四川省科技厅应用基础项目（2018JY0146，2019YFH0187）；深圳市重大国际合作项目（GJHZ20160301164521358）.
作者简介:董旭德，男，1994年生，硕士研究生，主要研究方向为计算机视觉、机器学习与深度学习网络。;许源平，男，1980年生，教授，主要研究方向为智能制造专家系统、知识库与知识工程、机器视觉。主持国家自然科学基金和四川省科技项目8项。发表学术论文50余篇。;舒红平,男，1974年生，教授，博士生导师，主要研究方向为软件开发环境与智能服务大数据。主持和参与了国家自然科学基金、9项973课题、四川省科技支撑计划项目、四川省青年科技基金等纵向项目12项。发表核心期刊以上论文近40篇。
通讯作者:许源平.E-mail:ypxu@cuit.edu.cn
更新日期/Last Update:
2019-04-25