期刊文献+

融合流形学习与相关反馈的人脸图像检索 被引量:3

Face Image Retrieval Integrating Manifold Learning with Relevance Feedback
下载PDF
导出
摘要 针对图像检索中视觉特征和语义信息中的"语义鸿沟"问题,提出一种融合流形学习和相关反馈的人脸图像检索算法.该算法充分考虑相关反馈提供的结合语义信息的正反例样本来发现图像样本之间的鉴别性流形,优化构建低维嵌入空间的特征向量,使得相关图像之间保持近邻关系,通过最大化不相关图像之间的距离,得到一个结合了用户语义理解的低维流形特征空间.实验结果表明:文中提出的算法有效地融合了图像视觉特征和语义信息,其性能明显优于反馈保局投影、增强联系嵌入等算法,其中前20个查询结果的检索精度提高了10个百分点以上. To narrow down the semantic gap between visual features and semantic information in the retrieval system of face image,a novel retrieval algorithm integrating the manifold learning with the relevant feedback is proposed.In this algorithm,the positive and negative samples containing semantic information,which are provided by the rele-vance feedback,are taken into consideration to achieve the discriminative manifold embedded in the image space,and a low-dimension manifold space with users' semantic comprehension is obtained by maximizing the gap between the uncorrelated images.Experimental results show that the proposed algorithm effectively integrates the visual features with the semantic information of images,and that it outperforms the algorithms such as the feedback-based locality-preserving projection and the augmented relation embedding,with a retrieval accuracy increasing by 10 points of percentage for the first 20 retrieval results.
出处 《华南理工大学学报(自然科学版)》 EI CAS CSCD 北大核心 2011年第5期91-96,共6页 Journal of South China University of Technology(Natural Science Edition)
基金 重庆市自然科学基金资助项目(CSTC2009BB2195) 重庆市科技攻关重点项目(CSTC2009AB2231) 重庆大学中央高校基本科研业务费资助项目(CDJRC10120012)
关键词 图像检索 相关反馈 语义信息 维数约简 流形学习 image retrieval relevance feedback semantic information dimensionality reduction manifold learning
  • 相关文献

参考文献14

  • 1李大湘,彭进业,贺进芳.基于视觉语义与RSSVM的图像检索[J].华南理工大学学报(自然科学版),2010,38(4):156-161. 被引量:4
  • 2贺广南,杨育彬.基于流形学习的图像检索算法研究[J].山东大学学报(工学版),2010,40(5):129-136. 被引量:3
  • 3He X F,Ma W Y,Zhang H J.Learning an image manifold for retrieval[C] //Proceedings of 12th ACM International Conference on Multimedia.New York:ACM Press,2004:17-23.
  • 4Huang H,Li J W,Feng H L.Subspaces versus submanifolds:a comparative study in small sample size problem[J].International Journal of Pattern Recognition and Artificial Intelligence,2009,23 (3):463-490.
  • 5Duda R O,Hart P E,Stork D G.Pattern classification[M].2nd ed.New York:Wiley-Interscience,2000:67-72.
  • 6罗斌,郑爱华,汤进.基于模糊多类SVM的图像检索相关反馈[J].华南理工大学学报(自然科学版),2008,36(9):107-112. 被引量:3
  • 7He X F,King O,Ma W Y,et al.Learning a semantic space from user's relevance feedback for image retrieval[J].IEEE Transactions on Circuit and Systems for Video Technology,2003,13 (1):39-48.
  • 8施智平,李清勇,史俊,史忠植.集成视觉特征和语义信息的相关反馈方法[J].计算机辅助设计与图形学学报,2007,19(9):1138-1142. 被引量:4
  • 9鲁珂,赵继东,吴跃,何晓飞.基于保局投影的相关反馈算法[J].计算机辅助设计与图形学学报,2007,19(1):20-24. 被引量:8
  • 10Lu K,He X F.Image retrieval based on incremental semi-supervised subspace learning[J].Pattern Recognition,2005,38 (11):2047-2054.

二级参考文献82

共引文献17

同被引文献20

  • 1Seung H S, Lee D D. The Manifold Ways of Perception[J]. Science, 2000, 290(5500): 2268-2269.
  • 2He Xiaofei, Niyogi P. Locality Preserving Projections[C]//Proc. of Annual Conference on Neural Information Processing System. Cambridge, USA: MIT Press, 2004: 327-334.
  • 3He Xiaofei. Incremental Semi-supervised Subspace Learning for Image Retrieval[C]//Proc. of the 12th Annual ACM Conference on Multimedia. New York, USA: ACM Press, 2004: 2-8.
  • 4Lin Yen-Yu, Liu Tyng-Luh, Chen Hwann-Tzong. Semantic Manifold Learning for Image Retrieval[C]//Proc. of the 13th Annual ACM International Conference on Multimedia. Singapore: ACM Press, 2005: 249-258,.
  • 5He Xiaofei, Cai Deng, Han Jiawei. Learning a Maximum Margin Subspace for Image Retrieval[J]. IEEE Transactions on Knowledge and Data Engineering, 2008, 20(2): 189-201.
  • 6Wang Can, Zhao Jun, He Xiaofei, et al. Image Retrieval Using Nonlinear Manifold Embedding[J]. Neurocomputing, 2009, 72(16/18): 3922-3929.
  • 7Wang J Z. Test Database[DB/OL]. [2011-08-10]. http://wang. ist.psu.edu/-jwang/test 1 .zip.
  • 8JunYANG,Shi-jiao ZHU. Narrowing Semantic Gap in Con-tent-Based Image Retrieval[C]. 2012 International Conferenceon Computer Distributed Control and Intelligent EnviromentalMonitoring, 2012:433-438.
  • 9SeungH S, Lee D D. The Manifold Ways of Perception [J].Science, 2000, 290(22): 2268-2269.
  • 10Yen-YuLin, Tyng-Luh Liu, Hwann-Tzong Chen. SemanticManifold Learning for Image Retrieva[C]. Proceedings of the13th Annual ACM International Conference on Multimedia,2005: 249-258.

引证文献3

二级引证文献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