ABSTRACT
The objective of Content-based Image Retrieval (CBIR) systems is to return the most similar images given an image query. In this scenario, accurately ranking collection images is of great relevance. In general, CBIR systems consider only pairwise image analysis, that is, compute similarity measures considering only pair of images, ignoring the rich information encoded in the relations among several images. This paper presents a novel re-ranking approach based on contextual spaces aiming to improve the effectiveness of CBIR tasks, by exploring relations among images. In our approach, information encoded in both distances among images and ranked lists computed by CBIR systems are used for analyzing contextual information. The re-ranking method can also be applied to other tasks, such as: (i) for combining ranked lists obtained by using different image descriptors (rank aggregation); and (ii) for combining post-processing methods. We conducted several experiments involving shape, color, and texture descriptors and comparisons to other post-processing methods. Experimental results demonstrate the effectiveness of our method.
- N. Arica and F. T. Y. Vural. Bas: a perceptual shape descriptor based on the beam angle statistics. Pattern Recogn. Lett., 24(9--10):1627--1639, 2003. Google ScholarDigital Library
- X. Bai, B. Wang, X. Wang, W. Liu, and Z. Tu. Co-transduction for shape retrieval. ECCV, 3:328--341, 2010. Google ScholarDigital Library
- S. Belongie, J. Malik, and J. Puzicha. Shape matching and object recognition using shape contexts. PAMI, 24(4):509--522, 2002. Google ScholarDigital Library
- P. Brodatz. Textures: A Photographic Album for Artists and Designers. Dover, 1966.Google Scholar
- R. da S. Torres and A. X. Falcao. Contour Salience Descriptors for Effective Image Retrieval and Analysis. Image and Vision Computing, 25(1):3--13, January 2007.Google ScholarCross Ref
- F. F. Faria, A. Veloso, H. M. Almeida, E. Valle, R. da S. Torres, M. A. Goncalves, and W. M. Jr. Learning to rank for content-based image retrieval. In MIR '10, pages 285--294, 2010. Google ScholarDigital Library
- J. Huang, S. R. Kumar, M. Mitra, W.-J. Zhu, and R. Zabih. Image indexing using color correlograms. In CVPR '97, page 762, 1997. Google ScholarDigital Library
- S. Ji, K. Zhou, C. Liao, Z. Zheng, G.-R. Xue, O. Chapelle, G. Sun, and H. Zha. Global ranking by exploiting user clicks. In SIGIR '09, pages 35--42, 2009. Google ScholarDigital Library
- B. H. Kontschieder Peter, Donoser Michael. Beyond pairwise shape similarity analysis. ACCV '09, pages 655--666, 2009. Google ScholarDigital Library
- V. Kovalev and S. Volmer. Color co-occurence descriptors for querying-by-example. In MMM '98, page 32, 1998. Google ScholarDigital Library
- L. J. Latecki, R. Lakmper, and U. Eckhardt. Shape descriptors for non-rigid shapes with a single closed contour. In CVPR, pages 424--429, 2000.Google ScholarCross Ref
- H. Ling and D. W. Jacobs. Shape classification using the inner-distance. PAMI, 29(2):286--299, 2007. Google ScholarDigital Library
- H. Ling, X. Yang, and L. J. Latecki. Balancing deformability and discriminability for shape matching. ECCV, 3:411--424, 2010. Google ScholarDigital Library
- Y.-T. Liu, T.-Y. Liu, T. Qin, Z.-M. Ma, and H. Li. Supervised rank aggregation. In WWW 2007, pages 481--490, 2007. Google ScholarDigital Library
- T. Ojala, M. Pietikäinen, and T. Mäenpää. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. PAMI, 24(7):971--987, 2002. Google ScholarDigital Library
- G. Park, Y. Baek, and H.-K. Lee. Re-ranking algorithm using post-retrieval clustering for content-based image retrieval. Information Processing and Management, 41(2):177--194, 2005. Google ScholarDigital Library
- D. C. G. Pedronette and R. da S. Torres. Exploiting contextual information for image re-ranking. CIARP, pages 541--548, 2010. Google ScholarDigital Library
- D. C. G. Pedronette and R. da S. Torres. Shape retrieval using contour features and distance optmization. In VISAPP, volume 1, pages 197--202, 2010.Google Scholar
- F. Perronnin, Y. Liu, and J.-M. Renders. A family of contextual measures of similarity between distributions with application to image retrieval. CVPR, pages 2358--2365, 2009.Google ScholarCross Ref
- T. Qin, T.-Y. Liu, X.-D. Zhang, D.-S. Wang, and H. Li. Global ranking using continuous conditional random fields. In NIPS, pages 1281--1288, 2008.Google Scholar
- O. Schwander and F. Nielsen. Reranking with contextual dissimilarity measures from representational bregmanl k-means. In VISAPP, volume 1, pages 118--122, 2010.Google Scholar
- R. O. Stehling, M. A. Nascimento, and A. X. Falcao. A compact and efficient image retrieval approach based on border/interior pixel classification. In CIKM '02, pages 102--109, 2002. Google ScholarDigital Library
- M. J. Swain and D. H. Ballard. Color indexing. IJCV, 7(1):11--32, 1991. Google ScholarDigital Library
- B. Tao and B. W. Dickinson. Texture recognition and image retrieval using gradient indexing. JVCIR, 11(3):327--342, 2000.Google ScholarDigital Library
- A. Temlyakov, B. C. Munsell, J. W. Waggoner, and S. Wang. Two perceptually motivated strategies for shape classification. CVPR, 1:2289--2296, 2010.Google Scholar
- Z. Tu and A. L. Yuille. Shape matching and recognition - using generative models and informative features. ECCV, pages 195--209, 2004.Google ScholarCross Ref
- J. van de Weijer and C. Schmid. Coloring local feature extraction. In ECCV, volume Part II, pages 334--348. Springer, 2006. Google ScholarDigital Library
- X. Yang, X. Bai, L. J. Latecki, and Z. Tu. Improving shape retrieval by learning graph transduction. ECCV, 5305:788--801, 2008.Google Scholar
- X. Yang, S. Koknar-Tezel, and L. J. Latecki. Locally constrained diffusion process on locally densified distance spaces with applications to shape retrieval. In CVPR, pages 357--364, 2009.Google ScholarCross Ref
Index Terms
- Exploiting contextual spaces for image re-ranking and rank aggregation
Recommendations
Using contextual spaces for image re-ranking and rank aggregation
This article presents two novel re-ranking approaches that take into account contextual information defined by the K-Nearest Neighbours (KNN) of a query image for improving the effectiveness of CBIR systems. The main contributions of this article are ...
Image re-ranking and rank aggregation based on similarity of ranked lists
In Content-based Image Retrieval (CBIR) systems, ranking accurately collection images is of great relevance. Users are interested in the returned images placed at the first positions, which usually are the most relevant ones. Collection images are ...
Combining re-ranking and rank aggregation methods for image retrieval
This paper presents novel approaches for combining re-ranking and rank aggregation methods aiming at improving the effectiveness of Content-Based Image Retrieval (CBIR) systems. Given a query image as input, CBIR systems retrieve the most similar images ...
Comments