ABSTRACT
Various unsupervised learning methods have been proposed with significant improvements in the effectiveness of image search systems. However, despite the relevant effectiveness gains, these approaches commonly require high computation efforts, not addressing properly efficiency and scalability requirements. In this paper, we present a novel unsupervised learning approach for improving the effectiveness of image retrieval tasks. The proposed method is also scalable and efficient as it exploits parallel and heterogeneous computing on CPU and GPU devices. Extensive experiments were conducted considering five different public image collections and several descriptors. This rigorous experimental protocol evaluates the effectiveness, efficiency, and scalability of the proposed approach, and compares it with previous methods. Experimental results demonstrate that high effectiveness gains (up to +29%) can be obtained requiring small run times.
- J. Almeida, R. da S. Torres, and N. J. Leite. BP-tree: An efficient index for similarity search in high-dimensional metric spaces. In CIKM, pages 1365--1368, 2010. Google ScholarDigital Library
- J. Almeida, D. C. G. Pedronette, and O. A. B. Penatti. Unsupervised manifold learning for video genre retrieval. In CIARP, pages 604--612, 2014.Google ScholarCross Ref
- N. Arica and F. T. Y. Vural. BAS: a perceptual shape descriptor based on the beam angle statistics. Pattern Recognition Letters, 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. In ECCV, volume 3, pages 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
- S. A. Chatzichristofis and Y. S. Boutalis. Cedd: color and edge directivity descriptor: a compact descriptor for image indexing and retrieval. In ICVS, pages 312--322, 2008. Google ScholarDigital Library
- S. A. Chatzichristofis and Y. S. Boutalis. Fcth: Fuzzy color and texture histogram - a low level feature for accurate image retrieval. In WIAMIS, pages 191--196, 2008. Google ScholarDigital Library
- R. da S. Torres and A. X. Falcâo. Content-Based Image Retrieval: Theory and Applications. Revista de Informática Teórica e Aplicada, 13(2):161--185, 2006.Google Scholar
- R. da S. Torres and A. X. Falcâo. Contour Salience Descriptors for Effective Image Retrieval and Analysis. Image and Vision Computing, 25(1):3--13, 2007.Google ScholarCross Ref
- J.-M. Geusebroek, G. J. Burghouts, and A. W. M. Smeulders. The amsterdam library of object images. International Journal of Computer Vision, 61(1):103--112, 2005. Google ScholarDigital Library
- R. Gopalan, P. Turaga, and R. Chellappa. Articulation-invariant representation of non-planar shapes. In ECCV, volume 3, pages 286--299, 2010. Google ScholarDigital Library
- D. C. Guimarâes Pedronette, J. Almeida, and R. Da S. Torres. A scalable re-ranking method for content-based image retrieval. Information Sciences, 265:91--104, May 2014. Google ScholarDigital Library
- J. Huang, S. R. Kumar, M. Mitra, W.-J. Zhu, and R. Zabih. Image indexing using color correlograms. In CVPR, pages 762--768, 1997. Google ScholarDigital Library
- J. Jiang, B. Wang, and Z. Tu. Unsupervised metric learning by self-smoothing operator. In ICCV, pages 794--801, 2011. Google ScholarDigital Library
- P. Kontschieder, M. Donoser, and H. Bischof. Beyond pairwise shape similarity analysis. In ACCV, pages 655--666, 2009. Google ScholarDigital Library
- V. Kovalev and S. Volmer. Color co-occurence descriptors for querying-by-example. In ICMM, 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. In ECCV, volume 3, pages 411--424, 2010. Google ScholarDigital Library
- Y. Liu, D. Zhang, G. Lu, and W.-Y. Ma. A survey of content-based image retrieval with high-level semantics. Pattern Recognition, 40(1):262 -- 282, 2007. Google ScholarDigital Library
- D. Lowe. Object recognition from local scale-invariant features. In ICCV, pages 1150--1157, 1999. Google ScholarDigital Library
- H. Lu, B. Ooi, and K. Tan. Efficient image retrieval by color contents. In ADB, pages 95--108, 1994.Google ScholarCross Ref
- D. Nistér and H. Stewénius. Scalable recognition with a vocabulary tree. In CVPR, volume 2, pages 2161--2168, 2006. 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. Pass, R. Zabih, and J. Miller. Comparing images using color coherence vectors. In ACM-MM, pages 65--73, 1996. 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
- D. C. G. Pedronette and R. da S. Torres. Exploiting pairwise recommendation and clustering strategies for image re-ranking. Information Sciences, 207:19--34, 2012. Google ScholarDigital Library
- D. C. G. Pedronette and R. da S. Torres. Image re-ranking and rank aggregation based on similarity of ranked lists. Pattern Recognition, 46(8):2350--2360, 2013. Google ScholarDigital Library
- D. C. G. Pedronette, R. da S. Torres, E. Borin, and M. Breternitz. Efficient image re-ranking computation on GPUs. In ISPA, 2012. Google ScholarDigital Library
- D. C. G. Pedronette, R. da S. Torres, E. Borin, and M. Breternitz. Rl-sim algorithm acceleration on GPUs. In SBAC, 2013. Google ScholarDigital Library
- R. O. Stehling, M. A. Nascimento, and A. X. Falcâo. A compact and efficient image retrieval approach based on border/interior pixel classification. In CIKM, pages 102--109, 2002. Google ScholarDigital Library
- M. J. Swain and D. H. Ballard. Color indexing. International Journal on Computer Vision, 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
- Z. Tu and A. L. Yuille. Shape matching and recognition - using generative models and informative features. In ECCV, pages 195--209, 2004.Google ScholarCross Ref
- J. van de Weijer and C. Schmid. Coloring local feature extraction. In ECCV. Google ScholarDigital Library
- J. Wang, Y. Li, X. Bai, Y. Zhang, C. Wang, and N. Tang. Learning context-sensitive similarity by shortest path propagation. Pattern Recognition, 44(10-11):2367--2374, 2011. Google ScholarDigital Library
- 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
- X. Yang, L. Prasad, and L. Latecki. Affinity learning with diffusion on tensor product graph. PAMI, PP(99):1, 2012. Google ScholarDigital Library
- K. Zagoris, S. Chatzichristofis, N. Papamarkos, and Y. Boutalis. Automatic image annotation and retrieval using the joint composite descriptor. In PCI, pages 143--147, 2010. Google ScholarDigital Library
Index Terms
- Effective, Efficient, and Scalable Unsupervised Distance Learning in Image Retrieval Tasks
Recommendations
Selection and Combination of Unsupervised Learning Methods for Image Retrieval
CBMI '17: Proceedings of the 15th International Workshop on Content-Based Multimedia IndexingThe evolution of technologies to store and share images has made imperative the need for methods to index and retrieve multimedia information based on visual content. The CBIR (Content-Based Image Retrieval) systems are the main solution in this ...
Unsupervised Distance Learning By Reciprocal kNN Distance for Image Retrieval
ICMR '14: Proceedings of International Conference on Multimedia RetrievalThis paper presents a novel unsupervised learning approach that takes into account the intrinsic dataset structure, which is represented in terms of the reciprocal neighborhood references found in different ranked lists. The proposed Reciprocal kNN ...
A scalable re-ranking method for content-based image retrieval
Content-based Image Retrieval (CBIR) systems consider only a pairwise analysis, i.e., they measure the similarity between pairs of images, ignoring the rich information encoded in the relations among several images. However, the user perception usually ...
Comments