期刊文献+

一种针对大规模网络图像的自动标注改善算法 被引量:2

An Algorithm for the Automatic Annotation Refinement on Large-Scale Web Images
下载PDF
导出
摘要 在对网络图像进行索引时,人们往往利用网页中图像周围的文字作为其近似标注信息,但是这些文字信息质量不高,不足以良好地描述图像内容。该文提出一种综合利用图像视觉特征、相关文本信息以及词汇间语义关系的方法对这些不精确的文本信息进行改善,从而提高图像的索引和搜索质量。在大规模数据集上的实验证明了所提出的方法能够有效改善图像的标注。 When Web images are indexed, the textual information in the hosting web pages are usually used as approximate image description. However, such information is not accurate enough. In this paper, a framework is proposed to utilize the visual content, the textual context, and the semantic relations between keywords to refine the image annotation. Experiments on large-scale dataset demonstrate the effectiveness of the proposed method.
作者 王斌 俞能海
出处 《电子与信息学报》 EI CSCD 北大核心 2009年第2期270-274,共5页 Journal of Electronics & Information Technology
基金 国家自然科学基金(60672056)资助课题
关键词 自动图像标注 标注改善 多模态学习 Automatic image annotation Annotation refinement Multimodality learning
  • 相关文献

参考文献13

  • 1Duygulu P, Barnard K, and Freitas J, et al.. Object recognition as machine translation: Learning a lexicon for a fixed image vocabulary, European Conference on Computer Vision, Copenhagen, Denmark, 2002: 97-112. 被引量:1
  • 2Jeon J, Lavrenko V, and Manmatha R. Automatic image annotation and retrieval using cross-media relevance models In Proceedings of Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Toronto, Canada, 2003: 119-126. 被引量:1
  • 3Wang X, Zhang L, and Jing F, et al.. AnnoSearch: image auto-annotation by search. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, USA, 2006, Vol. 2: 1483-1490. 被引量:1
  • 4Deschacht K and Moens M. Text analysis for automatic image annotation. 45th Annual Meeting of the Association of Computational Linguistics, Prague, Czech, 2007: 1000-1007. 被引量:1
  • 5Zhang R, Zhang Z, and Li M, et al.. A probabilistic semantic model for image annotation and multi-modal image retrieval, Springer Multimedia Systems, 2006, Vol. 12: 27-33. 被引量:1
  • 6Zhou D, Weston J, and Gretton A, et al.. Ranking on data manifolds. MPI Technical Report (113), Max Planck Institute for Biological Cybernetics, Ttibingen, Germany, June 2003. 被引量:1
  • 7Zhou D, Huang J, and Scholkopf B. Beyond pairwise classification and clustering using hypergraphs. MPI Technical Report (143), Max Planck Institute for Biological Cybernetics, Tubingen, Germany, 2005. 被引量:1
  • 8Tong H, He J, and Li M, et al.. Graph based multimodality learning. In Proceedings of ACM Multimedia, Singapore, 2005: 862-871. 被引量:1
  • 9Miller G A. WordNet: A lexical database for English. Communication of A CM, 1995, 38(11): 39-41. 被引量:1
  • 10Jiang J and Conrath D. Semantic similarity based on corpus statistics and lexical taxonomy. In Proceedings of International Conference Research on Computational Linguistics, Talpei, 1997. 被引量:1

同被引文献23

  • 1SUN J J, CHENG Y, DING Q,et al. Information retrieval [ M ]. Beijing: Science Press, 2004. 被引量:1
  • 2JIN Y H, KHAN L, WANG Lei, et al. Image annotations by combiningmultiple evidence & wordnet [ C ]//Proc of the 13th Annual ACM International Conference on Multimedia. New York:ACM Press,2005: 706 -715. 被引量:1
  • 3WANG Chang-hu, JING Feng,ZHANG Lei,et al. Image annotation refinement using random walk with restarts [ C ]//Proc of ACM International Conference on Multimedia. New York : ACM Press, 2006 : 647- 650. 被引量:1
  • 4WANG Yang, MEI Tao, GONG Shao-gang. Combining global, regional and contextual features for automatic image annotation [ J ]. Pattern Recognition ,2009,42 ( 2 ) :259-266. 被引量:1
  • 5BINCENT L,SOILLE P. Watersheds in digital spaces:an efficient algorithm based on immersion simulations[ J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1991,13 ( 6 ) :583-598. 被引量:1
  • 6KANUNGO T,MOUNT D M,NETANYAHU N S,et al. A local search approximation algorithm for K-means clustering[ C ]//Proc of the 18 th Annual ACM Symposium on Computational Geometry. New York: ACM Press ,2003 : 1-25. 被引量:1
  • 7TUAN D P. Image segmentation using probabilistic fuzzy C-means clustering [ C ]//Proc of International Conference on Image Processing. 2001:722-725. 被引量:1
  • 8SHI Jian-bo, MALIK J. Normalized cuts and image segmentation [ C ]//Proc of IEEE Conference on Computer Vision and Pattern Recognition. Washington DC :IEEE Computer Society, 1997:731-737. 被引量:1
  • 9SHI Jian-bo, MALIK J. Normalized cuts and image segmentation [ J ]. IEEE Trans on Pattern Analysis and Machine Intelligence, 20130,22 ( 8 ) :888-905. 被引量:1
  • 10Jin Y, Khan L, Wang L, et al. Image annotations by combining multiple evidence & WordNet [C]//Proc of ACM Multimedia. New York: ACM, 2005:706-715. 被引量:1

引证文献2

二级引证文献5

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