基于高斯过程模型的指节图像识别方法
作者:
基金项目:

国家自然科学基金(51475365);陕西省教育厅省级重点实验室科学研究计划项目(12JS071);陕西省自然科学基础研究计划(2017JM5088)


Finger Knuckles Image Recognition Method Based on Gaussian Process Model
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [18]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    在基于图像的人机交互智能装配的手势识别与动作跟踪中,手部关节的图像定位是基础,并且关节信息的准确性对手势描述和行为识别与理解有直接影响.针对指节图像特征分布具有较强随机性,利用同态滤波进行图像预处理,以增强图像特征.基于高斯过程模型对手部指节图像二类特征进行学习,用样本对象的聚类测度,学习数据分布的特征模型,将学习获得的两类特征模型作为图像特征的检测器,检测结果即为图像的两个似然值.将经过正负类样本标记过的两种模型似然值作为输入,直接依据估计结果对手部关节图像进行检测识别.通过对不同位置处的手部关节识别分析和测试库检测,结果表明,本文所述方法可以直接得到后验概率的分布,提高了目标识别的准确性和效率.

    Abstract:

    The positioning of finger knuckle in hand image is the basis for the hand gesture recognition and motion tracking in intelligent assembly by human-computer interaction with machine vision. The accuracy of hand knuckle information has direct influence on the gesture description and behavior recognition. Considering the random distribution characteristics of knuckle images, the image preprocessing has made by homomorphic filtering to enhance the image features. Classification feature learning of clustering set on knuckle image is finished based on the Gaussian process model. The characteristics model of the data distribution is learned with the clustering measure of the sample. The two type feature model from the feature learning is a detector for image feature, and the detecting results are the two likelihood values of the image. The finger knuckle target is recognized directly according to the estimation results while the two types model likelihood value as the input value which is marked by the positive and negative samples. The hand knuckle recognizing experiments with different location are held, and the knuckle detection is carried out with our own created test knuckle library. It shows from the experimental results that the posterior probability distribution can be obtained directly, and the recognition accuracy and efficiency of target are improved. The algorithm presented above is feasible.

    参考文献
    [1] Bhuyan MK, MacDorman KF, Kar MK, et al. Hand pose recognition from monocular images by geometrical and texture analysis. Journal of Visual Languages & Computing, 2015, 28:39-55, doi:10.1016/j.jvlc.2014.12.001.[DOI:10.1016/j.jvlc.2014.12.001]
    [2] Wang Y, Ewert D, Vossen R, et al. A visual servoing system for interactive human-robot object transfer. Journal of Automation and Control Engineering, 2015, 3(4):277-283, doi:10.12720/joace.3.4.277-283.[DOI:10.12720/joace.3.4.277-283]
    [3] Corrales JA, García Gómez GJ, Torres F, et al. Cooperative tasks between humans and robots in industrial environments. International Journal of Advanced Robotic Systems, 2012, 9:94. (请核对页码是否修改正确)[DOI:10.5772/50988]
    [4] Lenz C, Knoll A. Mechanisms and capabilities for human robot collaboration. Proceedings of the 23rd IEEE International Symposium on Robot and Human Interactive Communication. Edinburgh, UK. 2014. 666-671.[doi:10.1109/ROMAN.2014.6926329]
    [5] Tan JTC, Duan F, Kato R, et al. Safety strategy for human-robot collaboration:Design and development in cellular manufacturing. Advanced Robotics, 2010, 24(5-6):839-860, doi:10.1163/016918610X493633.[DOI:10.1163/016918610X493633]
    [6] 陆劲挺, 贾伟, 叶慧, 等. 指节纹识别综述. 模式识别与人工智能, 2017, 30(7):622-636, doi:10.16451/j.cnki.issn1003-6059.201707005.[DOI:10.16451/j.cnki.issn1003-6059.201707005]
    [7] Zhang L, Zhang L, Zhang D, et al. Online finger-knuckle-print verification for personal authentication. Pattern Recognition, 2010, 43(7):2560-2571, doi:10.1016/j.patcog.2010.01.020.[DOI:10.1016/j.patcog.2010.01.020]
    [8] Usha K, Ezhilarasan M. Hybrid detection of convex curves for biometric authentication using tangents and secants. Proceedings of the 3rd IEEE International Advance Computing Conference. Ghaziabad, India. 2013. 763-768.
    [9] Vishwakarma S, Agrawal A. A survey on activity recognition and behavior understanding in video surveillance. The Visual Computer, 2013, 29(10):983-1009, doi:10.1007/s00371-012-0752-6.[DOI:10.1007/s00371-012-0752-6]
    [10] 姚争为, 潘志庚. 基于体素的人手结构自动估测. 中国图象图形学报, 2014, 19(1):54-61, doi:10.11834/jig.20140107.[DOI:10.11834/jig.20140107]
    [11] Rehg JM, Kanade T. DigitEyes:Vision-based hand tracking for human-computer interaction. Proceedings of IEEE Worshop on Motion of Non-Rigid and Articulated Objects. Austin, TX, USA. 1994. 16-22
    [12] Mikić I, Trivedi M, Hunter E, et al. Human body model acquisition and tracking using voxel data. International Journal of Computer Vision, 2003, 53(3):199-223.
    [13] Wang L, Li C. Spectrum-based kernel length estimation for gaussian process classification. IEEE Trans. on Cybernetics, 2014, 44(6):805-816.
    [14] Bazi Y, Melgani F. Gaussian process approach to remote sensing image classification. IEEE Trans. on Geoscience and Remote Sensing, 2010, 48(1):186-197.
    [15] Hensman J, Matthews A, Ghahramani Z. Scalable variational Gaussian process classification. Proceedings of the 18th International Conference on Artificial Intelligence and Statistics (AISTATS). San Diego, CA, USA. 2014. 351-360.
    [16] He JJ, Gu H, Wang ZL. Bayesian multi-instance multi-label learning using Gaussian process prior. Machine Learning, 2012, 88(1-2):273-295, doi:10.1007/s10994-012-5283-x.[DOI:10.1007/s10994-012-5283-x]
    [17] Titsias MK. Variational learning of inducing variables in sparse Gaussian processes. Proceedings of the 12th International Conference on Artificial Intelligence and Statistics (AISTATS). Clearwater Beach, FL, USA. 2009. 567-574.
    [18] 陈春宁, 王延杰. 在频域中利用同态滤波增强图像对比度. 微计算机信息, 2007, 23(2-3):264-266.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

杨世强,闫雪萍.基于高斯过程模型的指节图像识别方法.计算机系统应用,2018,27(5):186-192

复制
分享
文章指标
  • 点击次数:2150
  • 下载次数: 2076
  • HTML阅读次数: 1264
  • 引用次数: 0
历史
  • 收稿日期:2017-09-08
  • 最后修改日期:2017-09-27
  • 在线发布日期: 2018-04-23
文章二维码
您是第11208049位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号