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

基于相关视觉关键词的图像自动标注方法研究 被引量：3

Automatic Image Annotation Based on Relevant Visual Keywords
在线阅读 下载PDF
导出
摘要 图像自动标注是计算机视觉与模式识别等领域中的重要问题.针对现有模型未对文本关键词的视觉描述形式进行建模,导致标注结果中大量出现与图像视觉内容无关的标注词等问题,提出了基于相关视觉关键词的图像自动标注模型VKRAM.该模型将标注词分为非抽象标注词与抽象标注词.首先建立非抽象标注词的视觉关键词种子,并提出了一个新方法抽取非抽象标注词对应的视觉关键词集合;接着根据抽象关键词的特点,运用提出的基于减区域的算法抽取抽象关键词对应的视觉关键词种子与视觉关键词集合;然后提出一个自适应参数方法与快速求解算法用于确定不同视觉关键词的相似度阈值;最后将上述方法相结合并用于图像自动标注中.该模型能从一定程度上解决标注结果中出现的大量无关标注词问题.实验结果表明,该模型在大多数指标上相比以往模型均有所提高. Automatic image annotation is a significant and challenging problem in pattern recognition and computer vision areas.At present,existing models can not describe the visual representations of corresponding Keywords,which would lead to a great number of irrelevant annotations in final annotation results.These annotation words are not related to any part of images in visual contents.A new automatic image annotation model（VKRAM） based on relevant visual Keywords is proposed to overcome the above problems.Our model divides each keyword into two categories：Abstract word or non-Abstract word.Firstly,we establish visual keyword seeds of each non-Abstract word,and then a new method is proposed to extract visual keyword collections by using corresponding visual seeds.Secondly,according to the traits of Abstract words,an algorithm based on subtraction regions is proposed to extract visual keyword seeds and corresponding collections of each Abstract word.Thirdly,we propose an adaptive parameters method and a fast solution algorithm to determine the similarity thresholds of each keyword.Finally,the combinations of the above methods are used to improve annotation performance.Experimental results conducted on Corel 5K datasets verify the effectiveness of the proposed annotation image model and it has improved the annotation results on most evaluation methods.
作者 柯逍 李绍滋 曹冬林
机构地区 福州大学数学与计算机科学学院 厦门大学智能科学与技术系
出处 《计算机研究与发展》 EI CSCD 北大核心 2012年第4期846-855,共10页 Journal of Computer Research and Development
基金 国家自然科学基金项目(60873179 60803078) 高等学校博士学科点专项科研基金项目(20090121110032) 深圳市科技计划研究项目(JC200903180630A ZYB200907110169A)
关键词 图像自动标注 视觉关键词 自适应阈值 相关模型 抽象标注词 非抽象标注词 〈Key words〉automatic image annotation visual keyword adaptive threshold relevance model Abstract annotation word non-Abstract annotation word
分类号 TP391 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献18

  • 1Zhao Yufeng,Zhao Yao,Zhu Zhenfeng. TSVM-HMM:Transductive SVM based hidden Markov model for automatic image annotation[J].Expert Systems with Applications,2009,(02):9813-9818.
  • 2Qi Xiaojun,Han Yutao. Incorporating multiple SVMs for automatic image annotation[J].Pattern Recognition,2007,(02):728-741.
  • 3路晶,马少平.使用基于多例学习的启发式SVM算法的图像自动标注[J].计算机研究与发展,2009,46(5):864-871. 被引量：19
  • 4Aodriluka M,Roth S,Schiele B. People-tracking-bydetection and people-detection-by-tracking[A].Piscataway,NJ:IEEE,2008.1-8.
  • 5Jim M,David G L. Object class recognition and localization using sparse features with limited receptive fields[J].International Journal of Computer Vision,2008,(01):45-57.
  • 6Kalanit G,Rory S. Object recognition:Insights from advances in fMRI methods[J].Current Directions in Psychological Science,2009,(02):73-79.
  • 7Dollar P,Wojek C,Schiele B. Pedestrian detection:A benchmark[A].Piscataway,NJ:IEEE,2009.304-311.
  • 8Doygulu P,Barnard K,Freitas J. Object recognition as machine translation:Learning a lexicon for a fixed image vocabulary[A].Beilin:Springer-Verlag,2002.97-112.
  • 9Shi J,Malik J. Normalized cuts and image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,(08):888-905.
  • 10Blei D,Ng A Y,Jordan M. Latent Dirichlet allocation[J].Journal of Machine Learning Research,2003.993-1022.

二级参考文献17

  • 1路晶,马少平.基于概念索引的图像自动标注[J].计算机研究与发展,2007,44(3):452-459. 被引量：10
  • 2Duygulu P, Barnard K, Freitas J de, et al. Object recognition as machine translation: Learning a lexicon for a fixed image vocabulary [G] //LNCS2353: Proe of ECCV. Berlin: Springer, 2002:97-112 .
  • 3Barnad K, Duygulu P, Fretias N, et al. Matching words and pictures [J]. Journal of Machine Learning Research, 2003, 3:1107-1135
  • 4Jeon J, Lavrenko V, Manmatha R. Automatic image annotation and retrieval using cross-media relevance models [C] //Proc of the 26th Annual Int ACM SIGIR Conf. New York: ACM, 2003:119-126
  • 5Pan J Y, Yang H J, Duygulu P, et al. Automatic image captioning [C]//Proc of the 2004 IEEE Int Conf on Multimedia and Expo (ICME'04). 2004:1987-1990
  • 6Carneiro G, Vaseoncelos N. Formulating semantics image annotation as a supervised learning problem [C]//Proc of IEEE Conf Computer Vision and Pattern Recognition (CVPR'05). Los Alamitos, CA: IEEE Computer Society, 2005 : 163-168
  • 7Dietterich T G, Lathrop R H, Lozano-Perez T. Solving the multiple-instance problem with axis-parallel rectangles [J]. Artificial Intelligence, 1997, 89(1-2): 31-71
  • 8Maron O, Lozano-Perez T. A framework for multipleinstance learning [G]. Advances in Neural Information Processing Systems 11. Cambridge: MIT Press, 1998: 570- 576
  • 9Zhang Q, Goldman S A. EMDD: An improved multipleinstance learning technique [G]. Advances in Neural Information Processing Systems 14. Cambridge, MA: MIT Press, 2002: 1073-1080
  • 10Yang C, Dong M, Fotouhi F. Region bsased image annotation through multiple-instance learning [C] //Proc of ACM Multimedia. New York: ACM, 2005:435-438

共引文献18

同被引文献25

  • 1程涛,施水才,王霞,吕学强.基于同义词词林的中文文本主题词提取[J].广西师范大学学报（自然科学版）,2007,25(2):145-148. 被引量：11
  • 2丁江伟,刘挺,卢志茂,等.隐马尔可夫模型和贝叶斯模型词义消歧对比研究[C]//全国第七届计算语言学联合学术会议论文集.北京:清华大学出版社,2003:214-220.
  • 3Turney P. Learning to extract keyphrases from text [ R ]. Technical Report ERB-1057. National Research Council, Institute for Information Technology, 1999. http ://wenku. baidu, com/Sala70ebb8f67clcfad6bSiO, html.
  • 4WAN Xiao-jun, YANG Jian-wu, XIAO Jian-guo. Towards an iterative reinforcement approach for simultaneous document summarization and keyword extraction [ C]//Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics. Stroudsburg: ACL,2007 : 552-559.
  • 5Makadia A, Pavlovic V, Kumar S. A new baseline for image annotation [C] //Proc of the 10th European Conf on Computer Vision. Berlin: Springer, 2008:316-329.
  • 6Nguyen N, Caruana R. Classification with partial labels [C] //Proc of the 14th ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining. New York: ACM, 2008: 551- 559.
  • 7He Xuming, Zemel R S. Learning hybrid models for image annotation with partially labeled data [C]//Proc of the 22nd Conf on Neural Information Processing Systems. New York: Curran Associates, 2008:625-632.
  • 8Guillaumin M, Mensink T, Verbeek J. Tagprop: Discriminative metric learning in nearest neighbor models for image auto-annotation [C] //Proc of the 12th Int Conf on Computer Vision. Piseataway, NJ: IEEE, 2009.1 309-316.
  • 9Verbeek J, Guillaumin M. Image annotation with TagProp on the MIRFLICKR set [C] //Proc of the 2nd ACM SIGMM Int Conf on Multimedia Information Retrieval. New York: Association for Computing Machinery, 2010 : 537-546.
  • 10Fan Jianping, Shen Yi, Zhou Ning. Harvesting large-scale weakly-tagged image databases from the web [C] //Proe of the 23rd IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE Computer Society, 2010:802-809.

引证文献3

二级引证文献9

计算机研究与发展
2012年 第4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