期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

应用小波变换的人脸光照补偿 被引量：15

Face illumination compensation based on wavelet transform
下载PDF
导出
摘要 提出了一种用于非均匀光照条件下人脸识别的光照补偿算法。该算法将人脸图像变换到对数域,并在对数域中计算二维小波变换,通过舍弃低频子带图像中的系数来实现人脸图像的非均匀光照补偿。由于人脸光照补偿是为了提高人脸识别性能,所以光照补偿的效果利用人脸识别率来表征。在Yale B人脸库中,本文方法的平均误识率可达到0.18%,比对数域离散余弦变换(DCT)光照补偿算法性能更佳;在CAS_PEAL人脸库中的实验结果表明,本文方法的性能与对数域DCT方法相近。 A novel illumination compensation algorithm for face recognition under nonuniform illumination conditions is presented. The face images are transformed from spatial domain to logarithm domain and 2-dimension wavelet transform is calculated by the algorithm. Then coefficients of low-frequency subband image are discarded for face illumination compensation in logarithm domain. Because the purpose of illumination compensation is to improve the performance of face recognition, the effect of face illumination compensation is defined by face recognition rate. The proposed algorithm is compared with the Discrete Cosine Transformation（DCT） method in logarithm domain in Yale B face database, the experimental results show that the average error rate of the proposed algorithm can reach 0.18%, which is lower than that of the DCT method. In addition, the experimental results in CAS_ PEAl. face database indicate that the performance of the proposed algorithm is equivalent to that of the DCT method.
作者 聂祥飞 谭泽富 郭军
机构地区 重庆三峡学院物理与电子工程学院 北京邮电大学信息工程学院
出处 《光学精密工程》 EI CAS CSCD 北大核心 2008年第1期150-155,共6页 Optics and Precision Engineering
基金 国家自然科学基金资助项目(No.60475007) 重庆市教委自然科学基金资助项目 重庆市科委自然科学基金资助项目 重庆三峡学院自然科学基金资助项目
关键词 人脸识别 人脸光照补偿 小波变换 face recognition face illumination compensation wavelet transform
分类号 TP391.4 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献22

  • 1PHILLIPS P J,MOON H,RIZVI S A,et al..The FERET evaluation methodology for face-recognition algorithms[J].IEEE Trans.on PAMI,2000,22(10):1090-1104.
  • 2PHILLIPS P J,GROTHER P,IMCHEALS R J,et al..FRVT 2002:evaluation report[R/OL].http://www.frvt.org/DLs/FRVT_2002_ EValuation_Report.pdf,2003.
  • 3WARRINGTON E,TAYLOR A.Two categorical stages of object recognition[J].Perception,1978,7:152-164.
  • 4LIU D H,LAM K M,SHEN L S.Illumination invariant face recognition[J].Pattern Recognition,2005,38:1705-1716.
  • 5GAO Y,LEUNG M K H.Face recognition using line edge map[J].IEEE Trans.on PAMI,2002,24(6):764-779.
  • 6GUO B,LAM K M,LIN K H,et al..Human face recognition based on spatially weighted hausdorff distance[J].Pattern Recognition Letters,2003,24:499-507.
  • 7ADINI Y,MOSES Y,ULLMAN S.Face recognition:the problem of compensation for changes in illumination direction[J].IEEE Trans.on PAMI,1997,19(7):721-732.
  • 8CHEN H,BELHUMEUR P,JACOBS D.In search of illumination invariants[C].In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2000:254-261.
  • 9BELHUMEUR P N,HESPANHA J P,KRIEGMAN D J.Eigenfaces vs.fisherfaces:recognition using class specific linear projection[J].IEEE Trans.on PAMI,1997,19(7):711-720.
  • 10SHASHUA A,RAVIV R T.The quotient image:class-based re-rendering and recognition with varying illuminations[J].IEEE Trans.on PAMI,2001,23(2):129-139.

二级参考文献47

  • 1张雷,杨润魁,黄廉卿.数字X光医学影像压缩技术[J].光学精密工程,2004,12(6):632-637. 被引量：4
  • 2Phillips P.J,Moon H,Rizvi S.A.et al.The FERET evaluation methodology for face-recognition algorithms.IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(10):1090～1104
  • 3Phillips P.J,Grother P,Micheals R.J.et al.FRVT 2002:Evaluation Report.http://www.frvt.org/DLs/FRVT _2002 _ Evaluation _Report.pdf,March 2003
  • 4Hallinan P..A low-dimensional representation of human faces for arbitrary lighting conditions.In:Proceedings of the CVPR'94,Seattle,Washington,1994,995～999
  • 5Basri R,Jacobs D..Lambertian reflectance and linear subspaces.In:Proceedings of the ICCV'01,Vancouver,Canada,2001,383～390
  • 6Ramamoorthi R..Analytic PCA construction for theoretical analysis of lighting variability in images of a lambertian object.IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(10):1～12
  • 7Ramamoorthi R,Hanrahan P..On the relationship between radiance and irradiance:Determining the illumination from images of a convex Lambertian object.Journal of the Optical Society of America A,2001,18(10):2448～2459
  • 8Blanz V,Vetter T..Face recognition based on fitting a 3D morphable model.IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(9):1～12
  • 9Sim T,Kanade T..Combining models and exemplars for face recognition:An illuminating example.In:Proceedings of the Workshop on Models Versus Exemplars in Computer Vision of CVPR'01,Kauai,Hawaii,2001
  • 10Zhao W.Y,Chellappa R..Illumination-insensitive face recognition using symmetric shape-from-shading.In:Proceedings of the CVPR'00,Hilton Head Island,South Carolina,2000,1286～1293

共引文献67

同被引文献133

引证文献15

二级引证文献122

光学精密工程
2008年 第1期

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