期刊文献+

基于非负稀疏表示的遮挡人耳识别 被引量:3

Ear Recognition under Random Occlusion via Non-negative Sparse Representation
下载PDF
导出
摘要 遮挡是人耳识别中一个难以回避的问题,当人耳被遮挡时绝大多数人耳识别算法性能会大大降低.借鉴人类视觉认知特性,将非负稀疏表示用于遮挡情况下的人耳识别,提出一种更为鲁棒的遮挡人耳识别方法.首先对训练人耳图像和待识别人耳图像进行下采样降维,然后将待识别人耳图像表示为由所有训练人耳图像构成的字典的非负稀疏线性组合,最后通过求解非负稀疏表示模型得到稀疏表示系数,根据测试人耳图像的重建误差进行识别.在USTB人耳图像库上的实验结果表明,当人耳图像被遮挡时,该方法具有更好的鲁棒性和更高的识别率. One challenging problem inevitable in real application is that the ears are often occluded by some objects such as hair or hat.In this paper,ageneral classification algorithm based on non-negative sparse representation is proposed to handle ear recognition under random occlusion.Unlike sparse representation based classification in which the input data are described as a combination of basis features involving both additive and subtractive components,the proposed classification paradigm expresses an input ear signal as a linear additive combination of all the training ear signals,and then classification is made according to the reconstruction error of the input ear image.The recognition performance for various levels of occlusion areas is investigated in which the location of occlusion is randomly chosen to simulate real scenario.Experimental results on USTB ear database reveal that when the ear is occluded,the proposed method exhibits great robustness and achieves better recognition performance.
出处 《计算机辅助设计与图形学学报》 EI CSCD 北大核心 2014年第8期1339-1345,1353,共8页 Journal of Computer-Aided Design & Computer Graphics
基金 国家自然科学基金(61170116 61005009) 中央高校基本科研业务费专项基金(FRF-SD-12-017A) 教育部博士点基金(20100006110014)
关键词 人耳识别 人耳遮挡 非负稀疏表示 ear recognition ear with random occlusion non-negative sparse representation
  • 相关文献

参考文献27

  • 1Kumar A,Chan T S T.Robust ear identification using sparse representation of local texture descriptors [J].Pattern Recognition,2013,46(1):73-85.
  • 2何国辉,甘俊英,李春芝,高建虎.人脸与虹膜特征层融合模型的研究[J].电子学报,2007,35(7):1365-1371. 被引量:15
  • 3Jain A,Hong L,Bolle R.On-line fingerprint verification [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(4):302-314.
  • 4Wagner A,Wright J,Ganesh A,et al.Towards a practical face recognition system:robust alignment and illumination by sparse representation [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(2):372-386.
  • 5Pflug A,Busch C.Ear biometrics:a survey of detection,feature extraction and recognition methods [J].IET Biometrics,2012,1(2):114-129.
  • 6Abaza A,Ross A,Herbert C,et al.A survey on ear biometrics [J].ACM Computing Surveys,2013,45(2):Article No.22.
  • 7Arbab-Zavar B,Nixon M S.On guided model-based analysis of ear biometrics[J].Computer Vision and Image Understanding,2011,115(4):487-502.
  • 8敦文杰,穆志纯.基于ICA的非线性自适应特征融合的人耳识别[J].计算机辅助设计与图形学学报,2009,21(3):382-388. 被引量:11
  • 9Islam S,Bennamoun M,Owens R A.et al.A review of recent advances in 3D ear and expression invariant face biometrics [J].ACM Computing Surveys,2012,44(3):Article No.14.
  • 10田莹,苑玮琦.尺度不变特征与几何特征融合的人耳识别方法[J].光学学报,2008,28(8):1485-1491. 被引量:14

二级参考文献59

共引文献52

同被引文献20

引证文献3

二级引证文献4

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