基于SVM和组合优化模型的手势识别

系统仿真学报 ›› 2016, Vol. 28 ›› Issue (8): 1812-1817.

基于SVM和组合优化模型的手势识别

蔡芝蔚, 吴淑燕, 宋俊锋

丽水学院工程与设计学院,浙江丽水 323000

收稿日期:2014-08-30 修回日期:2015-02-02 出版日期:2016-08-08 发布日期:2020-08-17
作者简介:蔡芝蔚(1979-),女,浙江温州,高工,研究方向为数字媒体;吴淑燕（1978-）,女,浙江龙泉,工程师,研究方向为数字媒体。
基金资助:
丽水市科技局公益项目(2013JYZB19)

Study on Hand Gesture Recognition and Portfolio Optimization Model Based on SVM

Cai Zhiwei, Wu Shuyan, Song Junfeng

College of Engineering and Design, Lishui University, Lishui 323000, China

Received:2014-08-30 Revised:2015-02-02 Online:2016-08-08 Published:2020-08-17

摘要/Abstract

摘要： 针对手势识别进行了相关研究,通过采用机器学习中的SVM(Support Vector Machine)算法对手势识别中的有关特征进行了提取,再利用ANN(Artifical Neural Network)、HMM(Hidden Markov Model)和DTW(Dynamic Time Wrapping)三种手势识别算法的组合优化思想对手势进行识别。实验结果表明,组合优化模型的手势识别方法具有较好的准确率,是一种有效的手势识别方法。

关键词: 手势识别, 支持向量机, 组合优化, 特征提取, 虚拟现实

Abstract: Hand gesture recognition was researched. The idea of extracting related features was proposed by using SVM algorithm in machine learning domain, and combination optimization method was used, which consists of ANN, HMM and DTW, to do hand gesture recognition. The experimental results show that portfolio optimization model based gesture recognition method has high accuracy and is very effective.

Key words: gesture recognition, support vector machine, combinatorial optimization, feature extraction, virtual reality

中图分类号:

TP391.41

蔡芝蔚, 吴淑燕, 宋俊锋. 基于SVM和组合优化模型的手势识别[J]. 系统仿真学报, 2016, 28(8): 1812-1817.

Cai Zhiwei, Wu Shuyan, Song Junfeng. Study on Hand Gesture Recognition and Portfolio Optimization Model Based on SVM[J]. Journal of System Simulation, 2016, 28(8): 1812-1817.

参考文献 15

[1]	姚远, 张林剑, 乔文豹, 等. 图像中手部样本标记与手势识别[J]. 计算机辅助设计与图形学学报, 2013, 25(12): 1810-1817.
[2]	王原, 汤勇明, 王保平, 等. 基于混合高斯模型的非固定握持姿势手势识别[J]. 东南大学学报自然科学版, 2014, 44(2): 239-243.
[3]	Akl A, Feng C, Valaee S.A novel accelerometer-based gesture recognition system[J]. IEEE Transactions Signal Processing (S1053-587X), 2011, 59(12): 6197-6205.
[4]	王西颖, 戴国忠, 张习文, 等. 基于-模型的复杂动态手势识别[J]. 软件学报, 2008, 19(9): 2302-2312.
[5]	张汗灵, 李红英, 周敏, 等. 融合多特征和压缩感知的手势识别[J]. 湖南大学学报自然科学版, 2013, 40(3): 87-92.
[6]	王德鑫, 石崇林, 张茂军, 等. 基于网和的多重触控手势识别[J]. 模式识别与人工智能, 2010, 23(3): 408-413.
[7]	Wang C C, Wang K C.Hand posture recognition using Adaboost with SIFT for human robot interaction[C]// Proceedings of International Conference on Advanced Robotics. Berlin, Germany: Springer-Verlag, 2008: 317-329.
[8]	Sun J, Xu W-B, Feng B.A global search strategy of quantum-behaved particle swarm optimization [C]// Proceedings of the 2004 IEEE Conference on Cybernetics and Intelligent Systems. Piscataway, USA: IEEE Press, 2004, 1: 111-116.
[9]	Nowak E, Jurie F, Triggs B.Sampling strategies for bag-offeatures image classification[C]// Proceedings of the 9th European Conference on Computer Vision in Computer Vision. Berlin, Germany: Springer, 2006: 490-503.
[10]	Song Y, Demirdjian D, Davis R.Continuous body and hand gesture recognition for natural human-computer interaction[J]. ACM Transactions on Interactive Intelligent Systems (S2160-6455), 2012, 2(1): 5-12.
[11]	任彧, 顾成成. 基于特征和的手势识别[J]. 科技通报, 2011, 27(2): 211-214.
[12]	董立峰, 阮军, 马秋实, 等. 基于不变矩和支持向量机的手势识别[J]. 微型机与应用, 2012, 31(6): 32-35.
[13]	石曼银. 一种基于向量机的手势识别算法[J]. 电子测试, 2013 (16): 24-25.
[14]	Rautaray S S, Agrawal A.Real time multiple hand gesture recognition system for human computer interaction[J]. International Journal of Intelligent Systems and Applications (S2333-9721), 2012, 5(8): 56-58.
[15]	于美娟. 基于SVM和HMM混合模型的动态手势识别技术研究 [D]. 天津: 天津师范大学, 2011.