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

DCT域上人脸光照正则化及识别 被引量：1

Lighting normalization for face recognition in DCT domain
下载PDF
导出
摘要 现有的光照正则化处理算法,都是在空间域中进行的,为避免海量图像解压缩的时间消耗,在JPEG图像上直接进行光照正则化处理,提高人脸识别效率,在DCT域上,基于三维辐照度方程,把差图像法推广到了DCT域上,并在DCT域上提出了分量图像法。实验表明:差图像法与分量图像法均能在DCT域中有效地削弱光照方向对人脸识别的负面影响。 All the existing lighting normalization algorithms are implemented in spatial domain. In order to save the time in images decompression and increase the speed in face recognition, we carried out lighting normalization for JPEG hnages directly. In this paper, we applied the Differential-image algorithm in the Discrete Cosine Transform （DCT） domain based on the 3-dimensional irradiance equation, and proposed Component-image method in DCT domain. Experiments show that the Differential-image algorithm and Component-image method in DCT domain can weaken the negative impact of face recognition from light directions effectively, improve the efficiency for face recognition in JPEG images.
作者 许嘉伟 冯国灿
机构地区 中山大学数学与计算科学学院
出处 《计算机应用》 CSCD 北大核心 2009年第1期47-50,共4页 journal of Computer Applications
基金 国家自然科学基金资助项目(60675007) 教育部重点基金资助项目(104145)
关键词 离散余弦变换 人脸识别 光照正则化 差图像 分量图像 Discrete Cosine Transform （DCT） face recognition lighting normalization, differential-image componentimage
分类号 TP391 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献15

  • 1ADINI Y, MOSES Y, ULLMAN S. Face recognition: the problem of compensating for changes in illumination direction [ J]. IEEE Transaction on PAMI, 1997, 19(7) : 721 - 732.
  • 2IKEUCHI K, HORN B K P. Numerical shape from shading and occluding boundaries [ J]. Artificial Intelligence, 1981 (17) : 141 - 1R4
  • 3BASRI R, JACOBS D W. Lambertian reflectance and linear subspaces [ J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2003,25(2): 218-233.
  • 4RAMAMOORTHI R, HANRAHAN P. On the relationship between radiance and irradiance: determining the illumination from images of a convex lambertian object [ J]. Journal of the Optical Society of America, 2001, 18(10) : 2448 -2459.
  • 5RIKLIN-RAVIV T, SHASHUA A. The quotient image: class based re-rendering and recognition with varying illuminations [ J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2001,23 (2): 129-139.
  • 6GEORGHIADES A S, KRIEGMAN D J, BELHUMEUR P N. Illumination cones for recognition under variable lighting: Faces [ J]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. [ S. l. ] : IEEE Press, 1998:52 -58.
  • 7GEORGHIADES A S, BELHUMEUR P N, KRIEGMAN D J. From few to many: Illumination cone models for face recognition under variable lighting and pose [ J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2001.23(6): 643 -660.
  • 8卿来云,山世光,陈熙霖,高文.基于球面谐波基图像的任意光照下的人脸识别[J].计算机学报,2006,29(5):760-768. 被引量：27
  • 9张海燕,王东木,宋克欧,官弼根.图像压缩技术[J].系统仿真学报,2002,14(7):831-835. 被引量：25
  • 10CCITT. JPEG-8-RS, JPEG technical specification , Revision 5 [ S]. 1990.

二级参考文献41

  • 1白跃彬,卢华斌,韩庆绵,赵玉明.图像压缩技术及其进展[J].微机发展,1996,6(4):24-27. 被引量：2
  • 2张亮.高速自适应分形图像压缩算法.98大连--香港国际计算机会议[M].,-.283-287.
  • 3秦烽,吴征,周峰,姚庆栋.分区IFS图像压缩编码[J].通信学报,1997,18(5):1-7. 被引量：11
  • 4Phillips 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
  • 5Phillips 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
  • 6Hallinan P..A low-dimensional representation of human faces for arbitrary lighting conditions.In:Proceedings of the CVPR'94,Seattle,Washington,1994,995～999
  • 7Basri R,Jacobs D..Lambertian reflectance and linear subspaces.In:Proceedings of the ICCV'01,Vancouver,Canada,2001,383～390
  • 8Ramamoorthi 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
  • 9Ramamoorthi 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
  • 10Blanz 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

共引文献50

同被引文献1

引证文献1

计算机应用
2009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