BAO Zhaohua,GAO Yuxiang,XIA Chaoyu,et al.Implementation of Static Gesture Recognition Algorithm based on Neural Network[J].Journal of Chengdu University of Information Technology,2019,(06):606-609.[doi:10.16836/j.cnki.jcuit.2019.06.008]
基于神经网络的静态手势识别算法实现
- Title:
- Implementation of Static Gesture Recognition Algorithm based on Neural Network
- 文章编号:
- 2096-1618(2019)06-0606-04
- Keywords:
- gesture recognition; neural network; corrosion; expansion; feature extraction
- 分类号:
- TP391.4
- 文献标志码:
- A
- 摘要:
- 随着物联网技术的发展,手势识别在当今的人机交互中起着至关重要的作用。针对复杂背景下手势识别率低、算法鲁棒性差的问题,提出了一种基于神经网络手势识别方法对26个英文字母实现静态手势识别,该算法由手势检测和特征提取及识别3部分构成。在手势检测部分,解决手势区域提取困难的问题; 在手势特征提取部分,通过肤色检测提取出手的轮廓信息的二值图像; 在识别阶段,使用从LeNet-5改进的CNN来识别手势。在自己制作的数据集下对神经网络进行训练,最终获得较高的识别率; 并在NUS-II和Marcel两个复杂背景的公共数据集上进行了验证实验,识别率分别达到95.31% 和98.10%。结果表明,该方法可以在复杂环境下对手势进行精确识别具有较高的稳定性。
- Abstract:
- With the development of Internet of things technology, gesture recognition plays a vital role in today’s human-computer interaction. Aiming at the problem of low recognition rate and poor algorithm robustness in complex background, this paper proposes a gesture recognition method based on neural network to achieve static gesture recognition of 26 English letters. The algorithm consists of gesture detection and feature extraction and recognition. In the gesture detection section, the problem of difficulty in extracting the gesture area is solved. In the gesture feature extraction section, the binary image of the contour information of the hand is extracted by the skin color detection. In the recognition phase, the gesture is recognized using the CNN improved from LeNet-5. The neural network was trained under the data set produced by ourselves, and finally the comparatively higher recognition rate was obtained. The verification experiments were carried out on common datasets of NUS-II and Marcel, which have complex background, and the recognition rates reached 95.31% and 98.10% respectively. The results show that the method can achieve high stability in the accurate recognition of gestures in complex environments.
参考文献/References:
[1] Liu Y,Zhang L,Zhang S.A hand gesture recognition method based on multi-feature fusion and template matching [J].Procedia Engineering,2012,29(4):1678-1684.
[2] Dai Y K,Zhou Z H,Chen X,et al.A novel method for simultaneous gesture segmentation an recognition based on HMM[C].Proceedings of the 2017 International Symposium on Intelligent Signal Processing and Communication Systems.Piscataway,NJ:IEEE,November 6-9,2017:684-688.
[3] Lü N,Yang Y J,Xu T.Sparse decomposition for data glove gesture recognition[C].Proceedings of the 2017 10th International Congress on Image and Signal Processing,BioMedical Engineering and Informatics(CISP-BMEI). Piscataway,NJ:IEEE,2017:1-5.
[4] Pisharady P K,Vadakkepat P,Loh A P.Attention based detection and recognition of hand postures against complex backgrounds[J].International Journal of Computer Vision,2013,101(3):403-419.
[5] Sangi P,Matilainen M,Silven O.Rotation tolerant hand pose recognition using aggregation of gradient orientations[M].Lecture Notes in Computer Science,Berlin,Germany:Springer,2016:257-267.
[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] Mohanty A,Rambhatla S S,Sahay R R.Deep gesture: Static hand gesture recognition using CNN[M].Advances in Intelligent Systems and Computing,Berlin,Germany:Springer,2017:449-461.
[8] Girshick R,Donahue J,Darrell T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C].2014 IEEE Conference on Computer Vision and Pattern Recognition,2014:580-587.
[9] Ren S,He K,Girshick R,et al.Faster R-CNN:towards real-time object detection with region proposal networks[C].International Conference on Neural Information Processing Systems.[S.l.]:MIT Press,2015:91-99.
[10] Redmon J,Divvala S,Girshick R,et al.You only look once:unified,real-time object detection[C].IEEE Conference on Computer Vision and Pattern Recognition,2016:779-788.
[11] Liu W,Anguelov D,Erhan D,et al.SSD:single shot multibox detector[C].European Conference on Computer Vision. Springer International Publishing,2016:21-37.
[12] Wei,Shih-En,et al.Convolutional Pose Machines[C].The Robotics Institute Carnegie Mellon University.CVPR,2016.
[13] Y.LeCun,L.Bottou L,Y.Bengio Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[14] 吴晴.基于改进的CNN和SVM手势识别算法研究[D].南昌:江西农业大学,2018.
[15] Jia J,Jiang J M,Wang D.Recognition of hand gesture based on Gaussian mixture model[C].International Workshop on Content-Based Multimedia Indexing.Piscataway,USA:IEEE,2008: 353-356.
相似文献/References:
[1]李姗姗,邓小波,丁继烈,等.基于SCIATRAN大气辐射传输模式的
卷云大气短波红外敏感性分析[J].成都信息工程大学学报,2017,(03):276.[doi:10.16836/j.cnki.jcuit.2017.03.008]
LI Shan-shan,DENG Xiao-bo,DING Ji-lie,et al.The Sensitivity Analysis of Cirrus Cloud Atmospheres Short Wave Infrared
based on SCIATRAN Atmospheric Radiative Transfer Model[J].Journal of Chengdu University of Information Technology,2017,(06):276.[doi:10.16836/j.cnki.jcuit.2017.03.008]
[2]谭诗雨,杨 玲,师春香,等.复杂背景下银行卡号识别方法研究[J].成都信息工程大学学报,2021,36(03):280.[doi:10.16836/j.cnki.jcuit.2021.03.007]
TAN Shiyu,YANG Ling,SHI Chunxiang,et al.Bank Card Number Recognition System under the Complex Background based on Deep Learning[J].Journal of Chengdu University of Information Technology,2021,36(06):280.[doi:10.16836/j.cnki.jcuit.2021.03.007]
[3]江金昊,刘海磊,王乙竹,等.基于Himawari-8卫星数据的青藏高原大气可降水量反演算法研究[J].成都信息工程大学学报,2022,37(05):494.[doi:10.16836/j.cnki.jcuit.2022.05.002]
JIANG Jinhao,LIU Hailei,WANG Yizhu,et al.Precipitable Water Vapor Retrieval Using Himawari-8 Satellite Observations over Tibetan Plateau[J].Journal of Chengdu University of Information Technology,2022,37(06):494.[doi:10.16836/j.cnki.jcuit.2022.05.002]
[4]任欣悦,何建新,张福贵,等.基于毫米波雷达的海雾观测及能见度反演算法研究[J].成都信息工程大学学报,2023,38(01):49.[doi:10.16836/j.cnki.jcuit.2023.01.008]
REN Xinyue,HE Jianxin,ZHANG Fugui,et al.Characteristic Analysis of a Sea Fog Process based on Millimeter-wave Radar and Research on Visibility Retrieval Algorithm[J].Journal of Chengdu University of Information Technology,2023,38(06):49.[doi:10.16836/j.cnki.jcuit.2023.01.008]
[5]张茂林,邓小波,刘海磊,等.基于全球预报系统气温的降尺度研究[J].成都信息工程大学学报,2023,38(06):720.[doi:10.16836/j.cnki.jcuit.2023.06.014]
ZHANG Maolin,DENG Xiaobo,LIU Hailei,et al.Downscaling Study based on GFS Air Temperature[J].Journal of Chengdu University of Information Technology,2023,38(06):720.[doi:10.16836/j.cnki.jcuit.2023.06.014]
备注/Memo
收稿日期:2019-06-09