|
|
|
Bundling features with multiple segmentations for
object-based image retrieval |
| WANG Jin-de, SHOU Li-dan, LI Xiao-yan, CHEN Gang |
| College of Computer Science & Technology, Zhejiang University, Hangzhou 310027, China |
|
|
|
Abstract In the area of objectbased image retrieval, the traditional visual words (VW) based methods neglected the spatial relationship among local features, resulting in the low accuracy. To overcome this problem, a novel method of bundling features with multiple segmentations was proposed. In our method, images were multiple segmented, and all segmentations were described by SIFT features fallen inside the area to generate bundling features. The bundling features were matched based on the VW vocabulary. An improved similarity metric was presented to measure the similarity between matched bundling features, and the degree of similarity was infused into the vector space model of VW method, to calculate the image similarity. Experiments show that the proposed method can exploit the space relationships among local features, and improve the retrieval accuracy greatly with no significant reduction in the efficiency.
|
|
Published: 17 March 2011
|
|
|
基于多重分割捆绑特征的目标图像检索
针对基于目标的图像检索（OBIR）领域中,传统的视觉关键词方法忽略了局部特征之间的空间关系信息,导致检索准确度不高的问题,提出一种基于多重分割捆绑特征的目标图像检索方法.通过对图像进行多重分割,各分割区块用它所包含的尺度不变特征变换(SIFT)特征集合来描述,生成包含空间关系信息的捆绑特征；根据视觉关键词词库匹配捆绑特征,并提出一种改进的相似性度量方法计算捆绑特征相似度,再将该相似度作为权重融入到视觉关键词方法的向量空间模型中,计算图像相似度并进行排序.结果表明,该方法能够有效利用局部特征之间的空间关系信息,在保证检索效率的同时,显著提高检索准确度.
|
|
| ［1］ SIVIC J, ZISSERMAN A. Video Google: a text retrieval approach to object matching in videos ［C］ ∥ Proceedings of International Conference on Computer Vision. Washington DC: ［s.n.］, 2003: 1470-1477.
［2］ JURIE F, TRIGGS B. Creating efficient codebooks for visual recognition ［C］ ∥ Proceedings of International Conference on Computer Vision. Beijing: ［s.n.］, 2005: 604-610.
［3］ NISTER D, STEWENIUS H. Scalable recognition with a vocabulary tree ［C］ ∥ Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2006: 2161-2168.
［4］ PHILBIN J, CHUM O, ISARD M, et al. Object retrieval with large vocabularies and fast spatial matching ［C］ ∥ Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis: IEEE, 2007: 1-8.
［5］ BORENSTEIN E, SHARON E, ULLMAN S. Combining topdown and bottomup segmentation ［C］ ∥ Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshop. Washington DC: IEEE, 2004: 46-53.
［6］ RUSSELL B C, EFROS A A, SIVIC J, et al. Using multiple segmentations to discover objects and their extent in image collections ［C］ ∥ Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2006: 1605-1614.
［7］ TANG Jiayu, LEWIS P H. Using multiple segmentations for image autoannotation ［C］ ∥ Proceedings of the 6th ACM International Conference on Image and Video Retrieval. Amsterdam: ACM, 2007: 581-586.
［8］ PANTOFARU C, SCHMID C, Hebert M. Object recognition by integrating multiple image segmentations ［C］ ∥ Proceedings of European Conference on Computer Vision. Marseille: Springer 2008: 481-494.
［9］ WU Wen, YANG Jie. Object fingerprints for content analysis with applications to street landmark localization ［C］ ∥ Proceedings of ACM International Conference on Multimedia. Vancouver: ACM, 2008: 169-178.
［10］ LOWE D. Distinctive image features from scaleinvariant keypoints ［J］. International Journal of Computer Vision, 2004, 60(2): 91-110.
［11］ YATES R B, NETO B R. Modern information retrieval ［M］. 7th ed. \
[S. l\]: Addison Wesley, 1999.
［12］ ZHENG Qingfang, GAO Wen. Constructing visual phrases for effective and efficient objectbased image retrieval ［J］. ACM Transactions on Multimedia Computing, Communications and Applications, 2008, 5(1): 1-19.
［13］ 高科,林守勋,张勇东,等.基于空间上下文的目标图像检索［J］.计算机辅助设计与图形学学报,2008,20(11)： 1452-1458.
GAO Ke, LIN Shouxun, ZHANG Yongdong, et al. Objectbased image retrieval using spatial context ［J］. Journal of ComputerAided Design and Computer Graphics, 2008, 20(11): 1452-1458.
［14］ WU Zhong, KE Qifa, ISARD M, et al. Bundling features for large scale partialduplicate web image search ［C］ ∥ Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Florida: IEEE, 2009.
［15］ MATAS J, CHUM O, URBAN M, et a1. Robust wide baseline stereo from maximally stable external regions ［C］ ∥ Proceedings of British Machine Vision Conference. Cardiff: IEEE, 2002： 384-396.
［16］ MEYER F. Color image segmentation ［C］ ∥ Proceedings of the International Conference on Image Processing and its Applications. Maastricht: IEEE 1992: 303-306.
［17］ SHI Jianbo, MALIK J. Normalized Cuts and image segmentation ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8): 888-905.
［18］ COMANICIU D, MEER P. Mean Shift: A robust approach toward feature space analysis ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(5): 603-619.
［19］ FELZENSZWALB P F, HUTTENLOCHER D P. Efficient graphbased image segmentation ［J］. International Journal of Computer Vision, 2004, 59(2): 167-181.
［20］ 杨彬蔚,陆系群.抗纹理噪声干扰的纺织印染图像分割技术［J］.浙江大学学报：工学版,2009,43(4)： 668-672.
YANG Binwei, LU Xiqun. Antitexturenoise segmentation technique for color textile images ［J］. Journal of Zhejiang University: Engineering Science, 2009, 43(4): 668-672.
［21］ GRIFFIN G, HOLUB A, PERONA P. Caltech256 object category dataset ［R］. California: California Institute of Technology, 2007. |
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
