期刊文献+

基于空间上下文的目标图像检索 被引量:9

Object-Based Image Retrieval Using Spatial Context
下载PDF
导出
摘要 提出了一种空间上下文描述与匹配方法,有效地提高了基于视觉关键词的图像检索中目标对象的可区分性.首先通过定义具有仿射协变性的空间邻域,得到自适应的多层空间上下文描述;然后提出模糊堆土机距离度量方法计算空间上下文相似性,以减少区块特征聚类错误对空间关系匹配的影响.在预处理阶段,基于熵值和自相似度进行噪声区块过滤.与已有方法相比,该方法的平均检索精度相对提高了10.8%. A new method of describing and matching spatial context is proposed to effectively improve the distinguishability of objects in visual words-based image retrieval. Firstly, we define an affine covariant spatial neighborhood to obtain effective spatial context description. Secondly, fuzzyearth mover's distance metric is presented to calculate their similarity, and reduces the effect of features' false clustering. Besides, noise regions are filtrated based on entropy and self-similarity as pretreatment. Experimental results demonstrate that, compared with existing methods, the relative improvement of our method's average retrieval precision is 10.8 %.
出处 《计算机辅助设计与图形学学报》 EI CSCD 北大核心 2008年第11期1452-1458,共7页 Journal of Computer-Aided Design & Computer Graphics
基金 国家“九七三”重点基础研究发展计划项目(2007CB311100) 国家“八六三”高技术研究发展计划(2007AA01Z416) 国家自然科学基金(60773056) 北京市科技新星工程(2007B071).
关键词 目标检索 空间上下文 模糊堆土机距离 object-based image retrieval spatial context fuzzy-earth mover's distance
  • 相关文献

参考文献10

  • 1Sivic J, Zisserman A. Video Google.. a text retrieval approach to object matching in videos[C] // Proceedings of Imernational Conference on Computer Vision, Washington, D C, 2003: 1470-1477
  • 2Philbin J, Chum O, Isard M, et al. Object retrieval with large vocabularies and fast spatial matehing[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, 2007:1-8
  • 3余莉,王润生,韩方剑.多分辨率形态学目标检测[J].计算机辅助设计与图形学学报,2006,18(6):849-853. 被引量:5
  • 4Lowe D. Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision, 2004, 60(2): 91-110
  • 5Fergus R, Li F F, Perona P, et al. Learning object categories from Google's image search[C] //Proceedings of International Conference on Computer Vision, Beijing, 2005:1816-1823
  • 6Mikolajczyk K, Tuytelaars T, Schmid C, et al. A comparison of affine region detectors [J]. International Journal of Computer Vision, 2006, 65(1):43-72
  • 7Zheng Q F, Wang W Q, Gao W. Effective and efficient object-based image retrieval using visual phrases[C] // Proceedings of the 14th ACM International Conference on Multimedia, Santa Barbara, 2006:77-80
  • 8Mikolajczyk K, Schmid C. A performance evaluation of local descriptors [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1615-1630
  • 9Matas J, Chum O, Urban M, et al. Robust wide baseline stereo from maximally stable extremal regions [ C] // Proceedings of British Machine Vision Conference, Cardiff, 2002:384-393
  • 10万丽莉,赵沁平,郝爱民.一种基于部件空间分布的三维模型检索方法[J].软件学报,2007,18(11):2902-2913. 被引量:13

二级参考文献10

  • 1潘翔,张三元,张引,叶修梓.一种基于拓扑连接图的三维模型检索方法[J].计算机学报,2004,27(9):1250-1255. 被引量:22
  • 2罗钟铉,刘成明.灰度图像匹配的快速算法[J].计算机辅助设计与图形学学报,2005,17(5):966-970. 被引量:72
  • 3Vincent L,Soille P.Watersheds in digital spaces:an efficient algorithm based on immersion simulations[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(6):583-598
  • 4Heijmans H J A M,Goutsias J.Nonlinear multiresolution signal decomposition schemes.Part 2:morphological wavelets[J].IEEE Transactions on Image Processing,2000,9(11):1897-1913
  • 5Tu Z,Chen X,Yuille A,et al.Image parsing:segmentation,detection,and object recognition[C] //Proceedings of the 9th IEEE International Conference on Computer Vision,Los Angeles,2003:18-25
  • 6Bravo M J,Farid H.Object segmentation by top-down processes[J].Visual Cognition,2003,10(4):471-491
  • 7Chen J H,Chen C S,Chen Y S.Fast algorithm for robust template matching with M-estimators[J].IEEE Transactions on Signal Processing,2003,51(1):230-243
  • 8Khabou M A,Gader P D,Keller J M.Ladar target detection using morphological shared-weight neural networks[J].Machine Vision and Applications,2000,11 (6):300-305
  • 9Roerdink J B T M,Meijster A.The watershed transform:definitions,algorithms and parallelization strategies[J].Fundamenta Informaticae,2000,41(1):187-228
  • 10肖俊,庄越挺,吴飞.基于细节层次与最小生成树的三维地形识别与检索[J].软件学报,2003,14(11):1955-1963. 被引量:10

共引文献16

同被引文献144

  • 1吴恩华.图形处理器用于通用计算的技术、现状及其挑战[J].软件学报,2004,15(10):1493-1504. 被引量:141
  • 2韩东峰,李文辉,郭武.基于潜在局部区域空间关系学习的物体分类算法[J].计算机学报,2007,30(8):1286-1294. 被引量:5
  • 3Matas J,Chum O,Urban M,et al.Robust wide-baseline stereo from maximally stable extremal regions[J].Image and Vision Computing,2004,22(10):761-767.
  • 4Mikolajczyk K,Tuytelaars T,Schmid C,et al.A comparison of affine region detectors[J].International Journal of Computer Vision,2006,65(1):43-72.
  • 5Sivic J,Zisserman A.VideoGoogle:a text retrieval approach to object matching in videos[C]//Proceedings of the 9th IEEE International Conference on Computer Vision,Washington D C,2003:1470-1477.
  • 6Nistér D,Stewénius H.Scalable recognition with a vocabulary tree[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition,New York,2006:2161-2168.
  • 7Philbin j,Chum O,Isard M,et al.Object retrieval with large vocabularies and fast spatial matching[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,Minneapolis,2007:1-8.
  • 8Zheng Q F,Wang W Q,Gap W.Effective and efficient object-based image retrieval using visual phrases[C]//Proceedings of the 14th ACM International Conference on Multimedia,Santa Barbara,2006:77-80.
  • 9Lowe D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
  • 10Mikolajczyk K,Schmid C.Scale & afflne invariant interest point detectors[J].International Journal of Computer Vision,2004,60(1):63-86.

引证文献9

二级引证文献31

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