期刊文献+

压缩域上人脸识别的研究 被引量:1

Face Recognition in Compressed Domain
下载PDF
导出
摘要 DCT变换被广泛采用在图象和视频压缩标准中(如JPEG,MPEG,H 261 H 263) 而对于这些压缩图象的处理,传统的手段是先解压到空间域,再进行处理和识别,因而增加了计算复杂性。针对这个问题,运用压缩域上图像处理技术,提出了人脸特征表达的方法,并构造DCT域上人脸识别系统。在人脸标准库FERET上的测试,提出的算法与经典的特征脸法和PCA+LDA法相比较,不仅提高了精度,而且降低了计算复杂性。 The discrete cosine transform is widely used in digital compression techniques for images and videos. The conventional approaches for the compressed image processing is to transfer the image to the spatial domain first, then to employ the traditional image processing techniques in spatial domain. This is certainly computational cost.A method is proposed for representing face feature directly extracted in compressed domain of JPEG, and a face recognition system in DCT domain is established. The experiments on FERET face database show the proposed algorithm can achieve higher recognition rate and lower the computational cost in comparison with that of eigenface and PCA+LDA.
出处 《中山大学学报(自然科学版)》 CAS CSCD 北大核心 2004年第5期16-19,共4页 Acta Scientiarum Naturalium Universitatis Sunyatseni
基金 教育部重点基金资助项目(104145) 广东省自然科学基金资助项目(031609)
关键词 人脸识别 余弦变换(DCT) 主成分分析(PCA) 压缩域 face recognition discrete cosine transform principal component analysis compressed domain
  • 相关文献

参考文献10

  • 1ZHAO W, CHELLAPPA R, ROSENFELD A, et al. Face recognition: a literature survey[C]. UMD CFAR Tech Report,2002: 948.
  • 2JIANG J, FENG G C. The spatial relationship of DCT coefficients between a block and its sub-blocks[J]. IEEE Trans on Signal Processing,2002, 50(5): 1160 - 1169.
  • 3EICKELER S, MULLER S, RIGOLL G. High quality face recognition in JPEG compressed images// Proc of the IEEE 1999 International Conference on Image Processing [ C].Kobe, Japan, 1999, 1:672 - 676.
  • 4李晓华,沈兰荪.基于压缩域的图像检索技术[J].计算机学报,2003,26(9):1051-1059. 被引量:22
  • 5FENG G C, JIANG J. Image extraction in DCT domain[J].IEE Proc Vis Image Signal Process, 2003,150( 1 ):
  • 6刘艳,李宏东.DCT域图象处理和特征提取技术[J].中国图象图形学报(A辑),2003,8(2):121-128. 被引量:21
  • 7AUGUSTEIJNM, CLEMENSLE, SHAWKA. Performance evaluation of texture measure for ground cover identification in satellite images by means of neural network classifier [ J ].IEEE Transactions on Geoscience & Remote Sensing, 1995,33(3) :616- 626.
  • 8DAVIDSALOMON.数据压缩原理与应用[M].北京:电子工业出版社,2003.6-35.
  • 9MANDAL M K, IDRIS F, PANCHANATHA S. A critical evaluation of image and video indexing techniques in the compressed domain[J]. Image and Vision Computing, 1999,17:513 - 529.
  • 10WALLACE G K. The JPEG still picture compression standard[J]. Communication of the ACM, 1991,34(4) :31

二级参考文献95

  • 1韩疆,全春来,李莲治,王岩.DCT域中特定几何变换的性质及其应用[J].系统工程与电子技术,1995,17(10):34-40. 被引量:1
  • 2Mandal M K. Wavelet based coding and indexing of images and video-Ph D dissertationS. University of Ottawa, Ottawa, Canada, 1998.
  • 3Chang Shih-Fu. Compressed-domain techniques for image/video indexing and manipulation. In: Proceedings of IEEE International Conference on Image Processing, Washington, DC,USA, 1995. 314-317.
  • 4Ma W Y, Manjunath B S, A comparison of wavelet transform features for texture image annotation, In: Proceedings of IEEE International Conference on Image Processing, Washington,DC,USA, 1995. 256-259.
  • 5Lee Moon-Chuen, Pun Chi-Man. Texture classification using dominant wavelet packet energy features. In: Proceedings of IEEE Southwest Symposium on Image Analysis and Interpretation, Austin, TX, USA, 2000. 301-304.
  • 6Chang T, Kuo C C J. Texture analysis and classification withtree-structured wavelet transform. IEEE Transactions on Image Processing,1993, 2(4) : 429-441.
  • 7Mandal M K, Aboulnasr T, Panchanathan S. Fast wavelet histogram techniques for image indexing. Journal of Computer Vision and Image Understanding. 1999, 75(1) : 99-110.
  • 8Smith J R, Chang S F. Automated binary texture feature setsfor image retrieval. Ins Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, Atlanta,1996. 2239-2242.
  • 9Seales W B, Yuan C J, Brown M. Efficient content extractionin compressed images. In: Proceedings of IEEE Workshop on Content-Based Access of Image and Video Libraries, San Juan,.Puerto Rico,1997. 52-58.
  • 10Yu Hong Heather. Visual image retrieval on compressed domain with Q-distance. In: Proceedings of IEEE International Conference on Computational Intelligence and Multimedia Applications, New Delhi, India, 1999. 1013-1016.

共引文献44

同被引文献6

  • 1KOHIR VV, DESAI UB. A transform domain face recognition approach[A]. Proceedings of the IEEE Region 10 Conference[ C].1999, Vol. 1:104 - 107.
  • 2WU JX, ZHOU ZH. Face Recognition with one training image per person[ J]. Pattern Recognition Letters, 2002, 23 (14): 1711 -1719.
  • 3HUANGJ, YUENPC, CHENWS, etal. Component-basedLDA Method for Face Recognition with One Training Sample[ A]. Proceedings of the IEEE International Workshop on Analysis and Modeling of Faces and Gestures[ C]. 2003. 120 - 126.
  • 4WISKOTT L, FELLOUS J-M, KRUGER N, et al. Face recognition by elastic bunch graph matching[ A]. International Conference on Image Processing[ C]. 1997 , Vol. 1: 129 - 132.
  • 5CHELLAPPA R, WILSON CL, SIROHEY S. Human and machine recognition of faces: A Survey[ J]. Proceedings of the IEEE, 1995,83(5): 705 - 741.
  • 6(美)DUDARO 李宏东 译.模式分类[M].北京:机械工业出版社,2003.383-388.

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