期刊文献+

非接触采集手形相对特征识别性能分析 被引量:1

Recognition performance analysis for the hand-shape relative features acquired with contactless method
在线阅读 下载PDF
导出
摘要 因非接触采集方式而产生的成像缩放与倾斜变形现象,使得成像后手形各特征的尺寸发生变化,从而造成绝对特征识别性能的显著下降。针对该问题作出了光学成像分析,证明了因倾斜变形现象产生的影响远小于缩放现象。因此在选用相对特征避免缩放现象的干扰后,利用类内方差均值和Fisher判别率,对变形后相对特征的稳定性和识别性能进行分析。实验结果表明,定义的相对特征可以作为稳定特征用于识别,同时经过小样本实验得到34个相对特征组成的向量,其识别率达到88.93%,说明该特征向量可以在小样本范围达到手形特征的有效识别,并可以作为手部识别的部分有效特征。 Image scaling and inclination deformation phenomena generated with contactless acquisition make the hand-shape feature of the image change in size, which causes the recognition performance of the absolute features de- creasing markedly. In order to solve this problem, the paper makes optical imaging analysis. It is proved that the influ- ence of inclination deformation is much less than that of the scaling. Therefore, after using the relative features to avoid the scaling phenomenon, the mean of intra-class standard deviation (MSD) and Finsher' s discriminant ratio (FDR) are used to analyze the stability and recognition performance of the relative features after inclination deforma- tion. The experiment results show that the defined relative features can be used as stable features for recognition. At the same time, the recognition rate of the vector consisting of 34 relative features in small sample experiment is 88.93% , which proves that the feature vector can achieve the effective recognition of the hand shape in small sample space and can be used as the partial effective features of hand recognition.
出处 《仪器仪表学报》 EI CAS CSCD 北大核心 2013年第9期2005-2012,共8页 Chinese Journal of Scientific Instrument
基金 国家自然科学基金(60972123) 高等学校博士点专项基金(20092102110002) 高等学校博士点专项基金(20122102120004) 辽宁省教育厅科研项目(2009A561) 沈阳市科技计划(F12-277-1-10) 沈阳市科技计划(F10-213-1-00)资助
关键词 非接触式采集 缩放现象 倾斜变形现象 手形相对特征 稳定性 contactless acquisition scaling phenomenon inclination deformation phenomenon hand-shape relative feature stability
  • 相关文献

参考文献19

  • 1ERDEM Y, ENDER K, BULENT S, et al. Shape-based hand recognition [ J ]. IEEE Transactions on Image Pro- cessing, 2006,15 ( 7 ) : 1803-1815.
  • 2A JAY K, DAVID C M W, HELEN C SH, et al. Personal authentication using hand images [ J ]. Pattern Recognition Letter,2006 (27) : 1478-1486.
  • 3E1-SALLAM A,SOHEL F, BENNAMOUN M. Robust pose invariant shape-based hand recognition [ C]. 2011 6th IEEE Conference on Industrial Electronics and Applica- tions ( ICIEA), Beijing, China ,2011:281-286.
  • 4KUKULA E, ELLIOTI" S. Implementation of hand geome- try:An analysis of user perspectives and system perform- ance [ J ]. IEEE Aerospace and Electronic System Maga- zine 2006,21 ( 3 ) :3-9.
  • 5HELIN D, BULENT S, ERDEM Y. A comparative analysis of global hand appearance-based person recognition [ J ]. Journal of Electronic Imaging, 2008,17 ( 1 ) :011018/1- 011018/19.
  • 6SUN L M, WEI W, LIU F. A Hand shape recognition method research based on gayssian mixture model [ C ]. International Conference on Optoelectronics and. Image Processing, Nanjing, China, 2010 : 15-19.
  • 7ANIL K J, NICOLAE D. Deformable matching of hand shapes for user verification [ C ]. Proceedings of Second International Conference on Audio and Video-Based Bio- metric Person Authentication ( ICIP ) , Kobe, Japan, 1999 : 857-861.
  • 8NONGLUK C, PIPAT P, PURIPANT R, et al. Personal verification and identification using hand geometry [ J ]. ECTI Transactions on Computer and Information Technol- ogy ,2005,1 (2) : 134-140.
  • 9WONG A L, SHIP CH. Peg-free hand geometry recogni- tion using hierarchical geometry and shape matching [ C ]. Proceedings of the IAPR Workshop on Machine Vision Applications, Nara, Japan ,2002:281-284.
  • 10VIVEK Y. Design of a hand geometry based verification system [ D ]. Thapar University, 2010.

二级参考文献106

共引文献28

同被引文献12

  • 1MIGUEL A, ANTONIO A, ANDRES V, et al.Biometric veri- fication/identification based on hands natural layout [ J ]. Image and Vision Computing,2008,26(4) :451-465.
  • 2NICOLAE D.A survey of biometric technology based on hand shape [ J ]. Pattern Recognition, 2009, 42 ( 11 ) : 2 797-2 806.
  • 3HAN C C.A hand-based personal authentication using a coarse-to-fine strategy [ J ]. Image and Vision Compu- ting, 2004,22 ( 11 ) : 909-918.
  • 4XIONG W,TOH K A,YAU W Y,et al.Model-guided de- formable hand shape recognition without positioning aids [ J] .Pattern Recognition ,2005,38(10) : 1 651 -1 664.
  • 5HAN C C,CHENG H L,LIN C L,et al.Personal authen- tication using palm-print features [ J ]. Pattern Recogni- tion, 2003,36 : 371-381.
  • 6MIGUEL A F, AYTHAMI M, ALBA D. An approach to SWIR hyperspectral hand biometrics [ J ]. Information Sciences, 2014,268 ( 1 ) : 3-19.
  • 7MALIK M, TARDI T. Gravity optimised particlefilter for hand tracking [ J ]. Pattern Recognition, 2014,47 ( 1 ) : 194-207.
  • 8MURAT A, MURAT E.AAM-based palm segmentation in unrestricted backgrounds and various postures for palmprint recognition [ J ]. Pattern Recognition Letters,2013,34(9):955-962.
  • 9YU P F,LI H Y,ZHOU H,et al.Palmprint recognition based on subclass discriminant analysis [ J ]. Lecture Notes in Electrical Engineering, 2014, 277 ( 1 ) : 465- 472.
  • 10陈燕新,戚飞虎.一种新的提取轮廓特征点的方法[J].红外与毫米波学报,1998,17(3):171-176. 被引量:21

引证文献1

二级引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部