[1]贾鹤鸣,朱传旭,张森,等.对偶树复小波与空域信息的手势识别分类研究[J].智能系统学报,2018,13(04):619-624.[doi:10.11992/tis.201708003]
 JIA Heming,ZHU Chuanxu,ZHANG Sen,et al.Research on gesture recognition and classification of dual-tree complex wavelet and spatial information[J].CAAI Transactions on Intelligent Systems,2018,13(04):619-624.[doi:10.11992/tis.201708003]
点击复制

对偶树复小波与空域信息的手势识别分类研究(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第13卷
期数:
2018年04期
页码:
619-624
栏目:
出版日期:
2018-07-05

文章信息/Info

Title:
Research on gesture recognition and classification of dual-tree complex wavelet and spatial information
作者:
贾鹤鸣1 朱传旭1 张森1 杨泽文2 何东旭2
1. 东北林业大学 机电工程学院, 黑龙江 哈尔滨 150040;
2. 哈尔滨工程大学 自动化学院, 黑龙江 哈尔滨 150001
Author(s):
JIA Heming1 ZHU Chuanxu1 ZHANG Sen1 YANG Zewen2 HE Dongxu2
1. College of Mechanical and Electrical Engineering, Northeast Forestry University, Harbin 150040, China;
2. College of Automation, Harbin Engineering University, Harbin 150001, China
关键词:
手势识别空域特征对偶树复小波特征融合分类器优化BD-SVM径向基核函数静态测试
Keywords:
gesture recognitionspatial featuredual-tree complex waveletfeature fusionclassifier optimizationBD-SVMradial basis kernel functionstatic test
分类号:
TP273
DOI:
10.11992/tis.201708003
摘要:
为提高手势识别中特征获取的有效性,本文提出空域特征与对偶树复小波变换特征相结合的融合特征,主要包括水平位置、竖直位置、长宽比、矩形度、Hu矩7个分量,及11维空域特征与对偶树复小波变换的16维特征进行融合后得到的27维特征。针对分类器优化算法,提出进行训练样本优选的最优距离-支持向量机(BD-SVM)分类方法。最后的实验结果表明,对“1~9”手势进行测试,当采用径向基核函数时,平均识别精度最高,为90.33%,平均识别时间为0.026 s,说明所提出的方法能够较好地进行静态手势识别,具有较高的训练速度和辨识精度。
Abstract:
To improve the validity of features obtained in gesture recognition, in this paper, we propose a fusion feature that combines spatial and dual-tree complex wavelet transform features. These features mainly include seven components (horizontal position, vertical position, aspect ratio, rectangular degree, Hu moments, etc.) and 27 dimensional features, comprising 11 dimensional spatial features and 16 dimensional dual-tree complex wavelet transform features. We employ the optimal distance support vector machine (BD-SVM) classification method to optimize training samples for the classifier optimization algorithm. The experimental results show that, in a test of gestures “1~9” using the RBF kernel function, the highest average recognition accuracy is 90.33% and the average recognition time is 0.026 s. These results reveal that the proposed method demonstrates excellent static gesture recognition, a high training speed, and accuracy in identification.

参考文献/References:

[1] BARROS P, PARISI G I, JIRAK D, et al. Real-time gesture recognition using a humanoid robot with a deep neural architecture[C]//201414th IEEE-RAS International Conference on Humanoid Robots. Madrid, Spain, 2014:646-651.
[2] DAVIS C C. Chronicler of the cavaliers:Some letters from and to William Alexander Caruthers, M. D. (1802-1846)[J]. The Virginia magazine of history and biography, 1947, 55(3):213-232.
[3] MIYASHITA T, SHINOZAWA K, HAGITA N. Gesture translation for heterogeneous robots[C]//20066th IEEE-RAS International Conference on Humanoid Robots. Genova, Italy, 2006:462-467.
[4] KAPUSCINSKI T, OSZUST M, WYSOCKI M. Hand gesture recognition using time-of-flight camera and viewpoint feature histogram[M]//KORBICZ J, KOWAL M (eds). Intelligent Systems in Technical and Medical Diagnostics. Berlin, Germany:Springer, 2014:403-414
[5] 谭台哲, 韩亚伟, 邵阳. 基于RGB-D图像的手势识别方法[J]. 计算机工程与设计, 2018, 39(2):511-515. TAN Taizhe, HAN Yawei, SHAO Yang. Gesture recognition method based on RGB-D image[J]. Computer engineering and design, 2018, 39(2):511-515.
[6] 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. 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.
[7] 赵磊, 周亦敏. 一种基于改进DTW-IMP算法的手势识别[J]. 软件导刊, 2017, 16(11):12-15, 21. ZHAO Lei, ZHOU Yimin. A gesture recognition based on improved DTW-IMP algorithm[J]. Software guide, 2017, 16(11):12-15, 21.
[8] 薛乐, 李立轻, 汪军. 应用频谱图的机织物纹理分析[J]. 纺织学报, 2015, 36(7):55-60. XUE Le, LI Liqing, WANG Jun. Study on woven fabric texture using frequency spectrum[J]. Journal of textile research, 2015, 36(7):55-60.
[9] 汪丹, 张亚非. SVM和BP算法在气体识别中的对比研究[J]. 传感技术学报, 2005, 18(1):201-204. WAN Dan, ZHANG Yafei. Research of Gas Classification Based on SVM Compared with BP[J]. Journal of transcluction technology, 2005, 18(1):201-204.
[10] 陈浩, 陈立辉, 毕笃彦, 等. BP网络和支持向量机在非线性函数逼近中的应用[J]. 航空计算技术, 2004, 34(3):27-30. CHEN Hao, CHEN Lihui, BI Duyan, et al. The appliance of BP-network and SVM in approach of non-linear function[J]. Aeronautical Computer Technique, 2004, 34(3):27-30. (本条文献为中文文献)
[11] LIANG Haonan, ZHANG Hanqi. Identification of slope stability based on the contrast of BP neural network and SVM[C]//20103rd IEEE International Conference on Computer Science and Information Technology. Chengdu, China, 2010:347-350.
[12] 周宇晴, 秦梦芝, 马志宏. 支持向量机和BP神经网络在可见-近红外光谱检测药品中的比较与应用[J]. 天津农学院学报, 2016, 23(2):49-52. ZHOU Yuqing, QIN Mengzhi, MA Zhihong. Comparison and application of support vector machine and BP neural network in visible-near infrared spectroscopy detection of drugs[J]. Journal of Tianjin agricultural university, 2016, 23(2):49-52.

相似文献/References:

[1]尤雅萍,成运,苏松志,等.基于谱域-空域结合特征和图割原理的高光谱图像分类[J].智能系统学报,2015,10(02):201.[doi:10.3969/j.issn.1673-4785.201410040]
 YOU Yaping,CHENG Yun,SU Songzhi,et al.Hyperspectral image classification based on spectral-spatial combination features and graph cut[J].CAAI Transactions on Intelligent Systems,2015,10(04):201.[doi:10.3969/j.issn.1673-4785.201410040]
[2]余思泉,曹江涛,李平,等.基于空间金字塔特征包的手势识别算法[J].智能系统学报,2015,10(03):429.[doi:10.3969/j.issn.1673-4785.201405054]
 YU Siquan,CAO Jiangtao,LI Ping,et al.Hand gesture recognition based on the spatial pyramid bag of features[J].CAAI Transactions on Intelligent Systems,2015,10(04):429.[doi:10.3969/j.issn.1673-4785.201405054]

备注/Memo

备注/Memo:
收稿日期:2017-08-03。
基金项目:中央高校基本科研业务费专项资金项目(2572014BB03);国家自然科学基金项目 (31470714,51609048);黑龙江省研究生教育创新工程项目(JGXM_HLJ_2016014).
作者简介:贾鹤鸣,男,1983年,副教授,博士,主要研究方向为非线性控制理论与信息检测技术;朱传旭,男,1993年,硕士研究生,主要研究方向为智能控制与信息处理技术;张森,男,1994年,硕士研究生,主要研究方向为智能控制与检测技术。
通讯作者:贾鹤鸣.E-mail:jiaheminglucky99@126.com.
更新日期/Last Update: 2018-08-25