期刊文献+

图像检索中的两层描述和非对称区域匹配 被引量:2

Two-Level Description and Unbalanced Region Matching in Image Retrieval
下载PDF
导出
摘要 在基于内容的图像检索中,需要描述图像中的空间信息从而克服仅基于全局特征的传统方法的局限.图像分割是得到图像空间描述信息的重要手段,但对于所有图像利用同一种分割结果的检索算法(单层描述方法)会受到图像分割算法精确度的影响而使性能受到限制.本文提出了基于图像的两层描述(包括粗略描述和精细描述)和非对称区域匹配的算法以减少不精确分割带来的不利影响.利用从70 0 0张通用图片库中随机选取的70 0幅查询图像而进行的统计实验结果表明此算法可以有效的提高检索效果. Research on integrating spatial information into content-based image retrieval is aimed at solving the problem caused by global feature based algorithm. Most systems derive the spatial information from image segmentation. However, the description of images based on one-level description (OLD) and the inevitable inaccuracy of segmentation results limit the performance. The proposed two-level description (TLD) describes images by a rough description and a detailed description to avoid improper spatial constrain caused by OLD. Similarity measurement based on unbalanced region matching (URM) is introduced in taking the advantage of TLD to reduce the influence of inaccurate segmentation. The performance of the system is illustrated by experimental results with 700 query images randomly selected from a database of 7000 general-purpose images.
出处 《电子学报》 EI CAS CSCD 北大核心 2005年第4期725-729,共5页 Acta Electronica Sinica
基金 国家自然科学基金(No.60172025)
关键词 基于内容的图像检索 两层描述 非对称区域匹配 Algorithms Content based retrieval Database systems Feature extraction Image segmentation Measurements
  • 相关文献

参考文献7

  • 1Carson C,Belongie S,Greenspan H.Blobworld:Image segmentation using expectation-maximization and its application to image querying[J].IEEE Trans PAMI,2002,24(8):1026-1038.
  • 2Wang J Z,Wiederhold G,Fischein O,et al.Content-based image indexing and searching using Daubechies' wavelets[J].Int.Journal Digital Libraries,1998,1(4):311-328.
  • 3Rubner Y,Tomasi C,Guibas L.Metric for distributions with applications to image databases[A].Proc Int Conf on Computer Vision[C].Bombay,India:IEEE,1998.59-66.
  • 4Mojsilovic A,Hu J,Soljanin E.Extraction of perceptually important colors and similarity measurement for image matching,retrieval and analysis[J].IEEE Trans on Image Processing,2002,11(11):1238-1248.
  • 5Dai S Y,Zhang Y J.Color image segmentation with watershed on color histogram and Markov random fields[A].Proc ICICS-PCM[C/CD].2003,Singapore:IEEE,p0240.
  • 6Swain M,Ballard D.Color indexing[J].Int Journal on Computer Vision,1991,7(1):11-32.
  • 7Hafner J,Sawhney H,Equitz W.Efficient color histogram indexing for quadratic form distance function[J].IEEE Trans PAMI,1995,17(7):729-736.

同被引文献30

  • 1杨育彬,陈世福,林珲.一种基于颜色连通的图像纹理检索新方法[J].电子学报,2005,33(1):57-62. 被引量:16
  • 2Datta R,Joshi D,et al.Image retrieval:Ideas,influences,and trends of the new age[J].ACM Computing Surveys,2008,40(2):1-60.
  • 3Zhon X,Huang T S.Relevance feedback in image retrieval:A comprehensive review[J].ACM Multimedia Syst J,2003,8:536-544.
  • 4Rocchio J J.Relevance Feedback in Information Retrieval[M].In Salton G.The SMART System.New York:Prentice-Hall,1971.313-323.
  • 5Ves E,Domingo J,et al.A novel Bayesian framework for relevance feedback in image content-based retrieval system[J].Pattern Recognition,2006,39:1622-1632.
  • 6Zhang L,et al.Support vector machine learning for image retrieval[A].Proc IEEE Int Conf Image processing[C].Thessaloniki,Greece:IEEE Press,2001.721-724.
  • 7Tao D,Tang X,et al.Asymmetric bagging and random subspace for support vector machines-based relevance feedback in image retrieval[J].IEEE Trans Pattern Analysis and Machine Intelligence,2006,28(7):1088-1099.
  • 8Zhang R,Zhang Z.BALAS:empirical Bayesian learning in relevance feedback for image retrieval[J].Image and Vision Computing,2006,24:211-223.
  • 9Tong S,Chang E.Support vector machine active learning forimage retrieval[A].Proc ACM Int Conf Multimedia[C].Ottawa,Canada:ACM Press,2001.107-118.
  • 10Zhou Z-H,Chen K-J,et al.Enhancing relevance feedback in image retrieval using unlabeled data[J].ACM Trans Information Systems,2006,24(2):219-244.

引证文献2

二级引证文献6

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