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

基于扩展生成语言模型的图像自动标注方法 被引量：9

Image Auto-Annotation via an Extended Generative Language Model
在线阅读 下载PDF
导出
摘要 使用最大权匹配算法,结合统计平滑技术,提出图像区域特征生成概率估计方法,并进一步对训练集中标注词之间的语义相关性(correlation)进行分析与度量,给出一种基于生成模型的图像标注算法.算法使用所提出的基于最大权匹配的图像生成概率估计方法得到较好的起始点,进而设计启发式迭代函数对词与词的相关性加以利用,最终提高标注词与图像的语义相关性.在现实世界图像数据库上的实验结果验证了所提出标注方法的有效性. In this paper, based on the statistical smoothing strategy, a image region feature generative prooability estimation method is proposed by exploiting maximum weight matching algorithm. By further analyzing and measuring the semantic correlations between words based on the training set, a novel image annotation algorithm for adopting the generative model is presented. The ftrst annotation keyword is obtained by using the proposed image region feature generative probability estimation algorithm. Then, a heuristic iterate function is proposed to exploit the keyword semantic correlation. Finally, the semantic correlation between the annotation and the image can be improved by our annotation algorithm. The proposed annotation approach is tested on a real-world image database, and promising results are achieved.
作者 王梅 周向东 张军旗 许红涛 施伯乐
机构地区 复旦大学计算机与信息技术系
出处 《软件学报》 EI CSCD 北大核心 2008年第9期2449-2460,共12页 Journal of Software
基金 国家自然科学基金 国家重点基础研究发展计划(973)~~
关键词 图像标注 生成模型 连续特征估计 最大权匹配 语义相关性 image annotation generative model continuous feature estimation maximum weight matching semantic correlation
分类号 TP311 [自动化与计算机技术—计算机软件与理论]
  • 相关文献

参考文献26

  • 1Duygulu P, Barnard K, de Freitas JFG, Forsyth DA. Object recognition as machine translation: Learning a lexicon for a fixed image vocabulary. In: Heyden A, ed. Proc. of the European Conf. on Computer Vision. Berlin: Springer-Verlag, 2002.97-112.
  • 2Jeon J, Lavrenko V, Manmatha R. Automatic image annotation and retrieval using cross-media relevance models. In: Proc. of the Int'l ACM SIGIR. Toronto: ACM Press, 2003. 119-126.
  • 3Feng SL, Manmatha R, Lavrenko V. Multiple Bernoulli relevance models for image and video annotation. In: Proc. of the IEEE Conf. Computer Vision and Pattern Recognition. Washington: IEEE Computer Society, 2004. 1002-1009.
  • 4Lavrenko V, Manmatha R, Jeon J. A model for learning the semantics of pictures. In: Sebastian T, Lawrence KS, Bernhard S, eds. Proc. of the Neural Information Processing Systems (NIPS). Vancouver, Whistler: MIT Press, 2004. 553-560.
  • 5Jin R, Chai JY, Si L. Effective automatic image annotation via a coherent language model and active learning. In: Henning S, Nevenka D, eds. Proc. of the Int'l Conf. on ACM Multimedia. New York: ACM Press, 2004. 892-899.
  • 6Jin Y, Khan L, Wang L, Awad M. Image annotations by combining multiple evidence & WordNet. In: Zhang HZ, Chua TS, eds. Proc. of the ACM Int'l Conf. on Multimedia. Singapore: ACM Press, 2005. 706-715.
  • 7Liu J, Li MJ, Ma WY, Liu QS, Lu HQ. An adaptive graph model for automatic image annotation. In: James ZW, Nozha B, eds. Proc. of the ACM SIGMM Int'l Workshop on Multimedia Information Retrieval. Santa Barbara: ACM Press, 2006. 61-69.
  • 8Monay F, Gatica-Perez D. On image auto-annotation with latent space models. In: Lawrence AR, Harrick MV, Thomas P, Prashant JS, John RS, eds. Proc. of the ACM Int'l Conf. on Multimedia. Berkeley: ACM Press, 2003. 275-278.
  • 9Monay F, Gatica-Perez D. PLSA-Based image auto annotation: Constraining the latent space. In: Henning S, Nevenka D, eds. Proc. of the Int'l Conf. on ACM Multimedia. New York: ACM Press, 2004. 348-351.
  • 10Srikanth M, Varner J, Bowden M, Moldovan D. Exploiting ontologies for automatic image annotation. In: Ricardo ABY, Nivio Z, Gary M, Alistair M, John T, eds. Proc. of the SIGIR. Salvador: ACM Press, 2005. 552-558.

同被引文献58

引证文献9

二级引证文献18

软件学报
2008年 第9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