期刊文献+

词包模型中视觉单词歧义性分析 被引量:11

Visual Words Ambiguity Analysis in BOW Model
下载PDF
导出
摘要 传统词包(BOW)模型中的视觉单词是通过无监督聚类图像块的特征向量得到的,没有考虑视觉单词的语义信息和语义性质。为解决该问题,提出一种基于文本分类的视觉单词歧义性分析方法。利用传统BOW模型生成初始视觉单词词汇表,使用文档频率、χ2分布和信息增益这3种文本分类方法分析单词语义性质,剔除具有低类别信息的歧义性单词,并采用支持向量机分类器实现图像分类。实验结果表明,该方法具有较高的分类精度。 Visual words in the traditional Bag of Word(BOW) model can be gotten by an unsupervised method of clustering the visual features.But one critical limitation of existing BOW is not concerned with the semantic natures of visual words.This paper proposes a visual words ambiguity analysis method based on text categorization.The codebook is generated by the BOW model.There are three ways of analysis——document frequency,χ2 distribution and information gains,and then they reduce the low information visual words after analyzing.It gets optimized visual words,the histogram formed by the frequency of visual words is used in image categorization task by the Support Vector Machine(SVM) classifier.Experimental results show that this method has higher classification accuracy.
出处 《计算机工程》 CAS CSCD 北大核心 2011年第19期204-206,209,共4页 Computer Engineering
基金 国家"973"计划基金资助项目(2006CB701303) 国家自然科学基金资助项目(41071256)
关键词 图像分类 视觉单词 文本分类 支持向量机 词包模型 image classification visual words text classification Support Vector Machine(SVM) Bag of Word(BOW) model
  • 相关文献

参考文献5

  • 1Pedro Q, Florent M, Jean-Marc O. A Thousand Words in a Scene[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2007, 29(9): 1575-1589. 被引量:1
  • 2Bosch A, Zisserman A. Scene Classification Using a Hybrid Generative/Discriminative Approach[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2008, 30(4): 712-727. 被引量:1
  • 3Hofmann T. Unsupervised Learning by Probabilistic Latent Semantic Analysis[J]. Journal of Machine Learning, 2001, 41(2): 177-196. 被引量:1
  • 4Yang Jun, Jiang Yugang. Evaluating Bag of Visual Words Representations in Scene Classification[C]//Proceedings of International Workshop on Multimedia Information Retrieval. [S. l.]: ACM Press, 2007: 197-206. 被引量:1
  • 5李瑜,郑敏娟,程国建.基于支持向量数据描述的分类方法研究[J].计算机工程,2009,35(1):235-236. 被引量:10

二级参考文献4

共引文献9

同被引文献101

  • 1杨筱林,姚鸿勋.基于多尺度形状描述子的手势识别[J].计算机工程与应用,2004,40(32):76-78. 被引量:3
  • 2胡迎松,朱阿柯,陈刚,陈中新.一种基于二维隐马尔可夫模型的图像分类算法[J].计算机应用,2005,25(4):760-762. 被引量:4
  • 3张良国,高文,陈熙霖,陈益强,王春立.面向中等词汇量的中国手语视觉识别系统[J].计算机研究与发展,2006,43(3):476-482. 被引量:11
  • 4姜峰,高文,姚鸿勋,赵德斌,陈熙霖.非特定人手语识别问题中的合成数据驱动方法[J].计算机研究与发展,2007,44(5):873-881. 被引量:5
  • 5GRAUMAN K, DARRELL T. Pyramid match kernels: discriminative classification with sets of image features [ C ]//Proc of IEEE International Conference on Computer Vision. 2005 : 1458-1465. 被引量:1
  • 6ZHANG J, MARSZALEK M, LAZEBNIK S, et al. Local features and kernels for classification of texture and object categories : a comprehensive study[ J]. International Journal of Computer Vision ,2007,73 (2) :213-238. 被引量:1
  • 7LI Fei-fei. Visual recognition:computational models and human psychophysics [ D ]. California : California Institute of Technology,2005. 被引量:1
  • 8LAZEBNIK S. Semi-local and global models for texture, object and scene recognition [ D ]. [ S.l. ] :University of Illinois at Urbana Champaign, 2006. 被引量:1
  • 9KIM G, FALOUTSOS C, HEBERT M. Unsupervised modeling and recognition of object categories with combination of visual contents and geometric similarity links [ C]//Proc of the 1st ACM International Conference on Multimedia Information Retrieval. New York: ACM Press ,2008:419-426. 被引量:1
  • 10LEORDEANU M, HEBERT M. A spectral technique for correspondence problems using pairwise constraints [ C ]//Proc of the 10th IEEE ICCV. Washington DC: IEEE Computer Society, 2005 : 1482- 1489. 被引量:1

引证文献11

二级引证文献48

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