| 127 | 0 | 20 |
| 下载次数 | 被引频次 | 阅读次数 |
针对人机交互问题,提出一种肤色检测与集成学习相结合的手势位置识别方法。利用目前比较成熟的Adaboost算法和基于HSV颜色空间的肤色检测算法相结合,并利用先识别人脸,再识别手掌位置的识别策略。有效的结合Adaboost和基于HSV颜色空间肤色检测两种算法的优势,并对这两种算法的缺陷进行了补足,很大程度上解决了Adaboost计算量大而导致识别周期长和基于HSV颜色空间的肤色检测高误检率的问题。实验结果表明,该算法运行到得出结果耗时0.465s,识别率高达95.21%。
Abstract：For the human-computer interaction problem,this paper proposes a gesture position recognition method that combines skin color detection and ensemble learning,which uses the combination of the currently mature Adaboost algorithm and the skin color detection algorithm based on the HSV color space.Meanwhile,utilized the recognition strategy of firstly identifying the human face and then identifying the palm position. Effectively combines the advantages of Adaboost and skin color detection algorithm based on the HSV color space,and decreased the defects of two algorithms,largely solving a large amount of Adaboost resulting in long recognition period and high error detected rate of based on the HSV color space.The experimental results showthat the algorithm takes 0. 465 s to reach the over,the recognition rate is as high as 95. 21%.
[1]Grimes G J.Digital data entry glove interface device[R].USA:Technical Report US Patent 4,1983:414-537.
[2]Grobel K,Assan M.Isolated sign language reco-gnition using hidden makov model[C]//IEEE Inter-national Conference on Computational Cybernetics and Simulation.USA,1997:162-167.
[3]杜堃,谭台哲.复杂环境下通用的手势识别方法[J].计算机应用,2016,36(7):1965-1970.
[4]范文兵,朱连杰.一种基于肤色特征提取的手势检测识别方法[J].现代电子技术,2017,40(18):85-88.
[5]杨红玲,宣士斌,梁竣程,等.基于肤色检测与卷积神经网络的手势识别[J].微型机与应用,2017,36(22):58-61.
[6]王龙,刘辉,王彬,等.结合肤色模型和卷积神经网络的手势识别方法[J].计算机工程与应用,2017,53(6):209-214.
[7]Michael Kearns,Leslie G Valiant.Learning Boo-lean Formulate or Finite Automata is as Hard as Factoring[R].USA:Technical Report TR-14-88 Harvard University Aiken Computation Laboratory,1988:330-400.
[8]Robert E.Schapire.The strength of weak learned ability[J].Machine Learning,1990,5(2):197-227.
[9]Freund Y,Schipare R E.A decision-theoretic generalization of online learning and an application to boosting[J].Journal of Computer and System Sciences,1995,55(1):23-37.
[10]P Viola,MJones.Robust real time object detection[C]//International Conference on Computer Vision(ICC-V),2001,57(2):87.
[11]曹莹,苗启广,刘家辰,等.Ada Boost算法研究进展与展望[J].自动化学报,2013,39(6):745-758.
[12]Papageorgious C,Oren M,Poggio T.A general of framework for Object Detection[C]//In International Conference on Computer Vision,India:2002,108(6):555-562.
[13]Viola P,Jones M.Rapid object detection using a boosted cascade of simple features[C]//International Conference on Computer Vision and Pattern Recognition,Kauai,HI,USA:2001,511-518.
[14]Viola P,Jones M.Robust real-time face detection[J].International Journal of Computer Vision,2004,57(2):137-154.
[15]Lienhart R,Kuranov A,Pisarevsky V.Empirical analysis of detection cascades of boosted classifiers for rapid object detection[C]//German Pattern Recognition Sysposium.Magdeburg,USA:2003:297-304.
[16]N Datal,B Triggs.Histograms of Oriented Gra-dients for Human Detection[C]//IEEE Computer Soc-iety Conference on Computer Vision&Pattern Recognition.USA,2005:886-893.
[17]Chai D,Nagan K N.Locating facial region of a head and shouders color image[C]//Proceedings of the 3rd IEEE International Conference on Automatic Face and Gesture Recognition,Japan:1998:124-129.
[18]张洪明,赵德斌,高文.基于肤色模型、神经网络和人脸结构模型的平面旋转人脸检测[J].计算机学报,2002,25(11):1250-1256.
[19]刘春生,常发亮,陈振学,等.改进的高斯肤色模型及其在人脸检测中的应用[J].仪器仪表学报,2012,33(5):1117-1121.
[20]张苗燕,王登飞,魏宗寿.一种改进的Ada Boost快速训练算法[J].西北工业大学学报,2017,35(6):1119-1124.
[21]马博宇,尉寅玮.基于Ada Boost算法的人脸识别系统的研究与实现[J].仪器仪表学报,2016,37(S1):162-167.
[22]文学志,方巍,郑钰辉.一种基于类Haar特征和改进Ada Boost分类器的车辆识别算法[J].电子学报,2011,39(5):1121-1126.
基本信息:
中图分类号:TP391.41;TP18
引用信息:
[1]常镶石,胡玉兰.一种实时手势位置识别方法研究[J].沈阳理工大学学报,2018,37(04):1-6.
基金信息:
国家自然基金资助项目(61373089;61672360)