期刊文献+

基于距离度量学习的DCT域JPEG图像检索 被引量:6

JPEG images retrieval in DCT domain based on Distance Metric Learning
在线阅读 下载PDF
导出
摘要 由于特征有限,传统基于欧式距离的压缩域检索性能并不理想。本文引入距离度量学习技术,研究压缩域图像检索,提出了一种基于距离度量学习的离散余弦变换(DCT)域联合图像专家小组(JPEG)图像检索方法。首先,提出了一种更有效的DCT域特征提取方法;其次,运用距离度量学习技术训练出一个更加有效的度量矩阵进行检索。在Corel5000上的图像检索实验表明,新方法有效提高了检索准确度。 Due to limited features extracted from compression domain, the conventional Euclidean distance based retrieval performance in compressed-domain is not satisfactory. The Distance Metric Learning(DML) is introduced to compressed-domain images retrieval and a DML based Discrete Cosine Transform(DCT) domain retrieval for Joint Photographic Experts Group(JPEG) images is developed. Firstly, we propose a more effective DCT domain features extraction method, and then the DML is applied to train a more efficient metric matrix for retrieval. Retrieval experiment on Corel5000 images database demonstrates that the approach proposed can effectively improve the retrieval accuracy.
出处 《太赫兹科学与电子信息学报》 2014年第1期112-118,共7页 Journal of Terahertz Science and Electronic Information Technology
基金 全军军事学研究生课题资助项目(YJS1062)
关键词 距离度量学习 图像检索 离散余弦变换域 联合图像专家小组图像 Distance Metric Learning images retrieval Discrete Cosine Transform domain Joint Photographic Experts Group
作者简介 吕清秀(1985-),男,甘肃省环县市人,在读硕士研究生,主要研究方向为智能信息处理、图像检索.email:lv_q_x@163.com. 李弼程(1971-),男,湖南省湘潭市人,博士,教授,主要研究方向为智能信息处理. 高毫林(1979-),男,河南省新郑市人,在读博士研究生,主要研究方向为智能信息处理.
  • 相关文献

参考文献18

  • 1胡学龙,陈爱民,周国华.一种改进的颜色匹配对图像检索算法[J].信息与电子工程,2003,1(4):265-268. 被引量:2
  • 2徐志杰,蔡晓霞.基于DCT系数统计特性的JPEG图像隐写分析[J].信息与电子工程,2010,8(1):79-83. 被引量:1
  • 3Bae H J,Jung S H. Image retrieval using texture based on DCT[C]// Proceedings of 1997 International Conference onInformation,Communications and Signal Processing. Singapore:[s.n.], 1997:1065-1068.
  • 4Lay J A,Ling G. Image retrieval based on energy histograms or the low frequency DCT coefficients[C]// Proceedings ofIEEE International Conference on Acoustics,Speech and Signal Processing. Phoenix:IEEE, 1999:3009-3012.
  • 5黄祥林,沈兰荪.基于DCT压缩域的纹理图像分类[J].电子与信息学报,2002,24(2):216-221. 被引量:27
  • 6Feng Guocan,Jiang Jianmin. JPEG compressed image retrieval via statistical features[J]. Pattern Recognition, 2003,36(4):977-985.
  • 7Tsai Tienwei,Huang Yo-Ping. Image Retrieval Based on Dominant Texture Features[C]// 2006 IEEE International Symposiumon Industrial Electronics. Taipei:IEEE, 2006:441-446.
  • 8Chen Weilong,Er Meng Joo,Wu Shiqian. PCA and LDA in DCT Domain[J]. Pattern Recognition Letters, 2005,26(15):2474-2482.
  • 9Cong Bai,Kidiyo Kpalma,Joseph Ronsin. Analysis of histogram descriptor for image retrieval in DCT domain[C]//Proceeding of the 4th International Conference on Intelligent Interactive Multimedia Systems and Services. Piraeus,Greece:Springer, 2011,11:227-235.
  • 10Ying Y,Li P. Distance metric learning with eigenvalue optimization[J]. Journal of Machine Learning Research, 2012,13:1–26.

二级参考文献14

  • 1胡守仁 余少波.神经网络导论[M].长沙:国防科技大学出版社,1992.113-129.
  • 2Upham D. JPEG-JSteg-V4[CP/OL]. (1993-05-25)[2009-11-02]. http://www.funet.fi/pub/crypl/stegan.graphy/jpeg-jsteg-v4.diff.gz.
  • 3Sallee P. Model-Based Steganography[C]//Proceedings of International Workshop on Digital Watermarking. Berlin: Springer-Verlag, 2004:154-167.
  • 4Westfeld A. F5-a steganography algorithm: high capacity despite better steganalysis[C]//Proceedings of 4th Information Hiding International Workshop. Berlin: Springer-Verlag, 2001,LNC2137:289-302.
  • 5Fridrich J,Goljan M,Hogea D. Steganalysis of JPEG Images: Breaking the F5 Algorithm[C]//Proceedings of the 5th Information Hiding Workshop. Berlin: Springer-Verlag, 2002:310-323.
  • 6Pevny T,Fridrich J. Towards Multi-Class Blind Steganalyzer for JPEG Images[C]~~ Proceedings of International Workshop on Digital Watermarking. Berlin: Springer-Verlag, 2005:39-53.
  • 7[2]M J Swain, D H Ballard. Color indexing[J]. Intl.J.Comput.Vis, 1991,7(1): 11-32.
  • 8[3]M J Swain ,D H Ballard. Indexing via Color Histograms[A]. In Proc ICCV90[C].1990,390-393.
  • 9[4]Y Rui,TS Huang,SF Chang.Image Retrieval:Current Techniques,Promising Directions and Open Issues[J].Journal of Visual Communication and Image Representation,1999,10:39-62.
  • 10柳伟,李国辉,曹莉华.一种基于内容的图象检索方法的实现[J].中国图象图形学报(A辑),1998,3(4):304-308. 被引量:20

共引文献28

同被引文献40

引证文献6

二级引证文献12

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