Eficácia, Eficiência e Escalabilidade em Método de Aprendizado Não Supervisionado de Busca de Imagens

  • Lucas Valem UNESP
  • Daniel Pedronette UNESP

Resumo


Vários métodos de aprendizado não supervisionado têm sido propostos obtendo melhorias significativas na eficácia de sistemas de busca de imagens. No entanto, apesar do considerável ganho de eficácia, esses métodos geralmente requerem altos custos computacionais, não contemplando adequadamente requisitos de eficiência e escalabilidade. Esse trabalho de iniciação científica propˆos um método de aprendizado não supervisionado que, apesar de ganhos significativos de eficácia, também considera requisitos de eficiência e escalabilidade. Conceitos de computação paralela e heterogênea, utilizando CPUs e GPUs, foram aplicados no desenvolvimento do trabalho.

Referências

Almeida, J., da S. Torres, R., and Leite, N. J. (2010). BP-tree: An efficient index for similarity search in high-dimensional metric spaces. In CIKM, pages 1365–1368.

Arica, N. and Vural, F. T. Y. (2003). BAS: a perceptual shape descriptor based on the beam angle statistics. Pattern Recognition Letters, 24(9-10):1627–1639.

Brodatz, P. (1966). Textures: A Photographic Album for Artists and Designers. Dover. Chatzichristofis, S. A. and Boutalis, Y. S. (2008a). CEDD: color and edge directivity descriptor: a compact descriptor for image indexing and retrieval. In ICVS, pages 312–322.

Chatzichristofis, S. A. and Boutalis, Y. S. (2008b). Fcth: Fuzzy color and texture histogram - a low level feature for accurate image retrieval. In WIAMIS, pages 191–196.

Datta, R., Joshi, D., Li, J., and Wang, J. Z. (2008). Image retrieval: Ideas, influences, and trends of the new age. ACM Computing Surveys, 40(2):5:1–5:60.

Geusebroek, J.-M., Burghouts, G. J., and Smeulders, A. W. M. (2005). The amsterdam library of object images. International Journal of Computer Vision, 61(1):103–112.

Gopalan, R., Turaga, P., and Chellappa, R. (2010). Articulation-invariant representation of non-planar shapes. In ECCV, volume 3, pages 286–299.

Huang, J., Kumar, S. R., Mitra, M., Zhu, W.-J., and Zabih, R. (1997). Image indexing using color correlograms. In CVPR, pages 762–768.

Kovalev, V. and Volmer, S. (1998). Color co-occurence descriptors for querying-by-example. In ICMM, page 32.

Latecki, L. J., Lakmper, R., and Eckhardt, U. (2000). Shape descriptors for non-rigid shapes with a single closed contour. In CVPR, pages 424–429.

Ling, H. and Jacobs, D. W. (2007). Shape classification using the inner-distance. PAMI, 29(2):286–299.

Ling, H., Yang, X., and Latecki, L. J. (2010). Balancing deformability and discriminability for shape matching. In ECCV, volume 3, pages 411–424.

Liu, Y., Zhang, D., Lu, G., and Ma,W.-Y. (2007). A survey of content-based image retrieval with high-level semantics. Pattern Recognition, 40(1):262 – 282.

Lowe, D. (1999). Object recognition from local scale-invariant features. In ICCV, pages 1150–1157.

Lu, H., Ooi, B., and Tan, K. (1994). Efficient image retrieval by color contents. In ADB, pages 95–108.

Nistér, D. and Stewénius, H. (2006). Scalable recognition with a vocabulary tree. In CVPR, volume 2, pages 2161–2168.

Ojala, T., Pietikäinen, M., andMäenpää, T. (2002). Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. PAMI, 24(7):971–987.

Pass, G., Zabih, R., and Miller, J. (1996). Comparing images using color coherence vectors. In ACM-MM, pages 65–73.

Pedronette, D. C. G. and Torres, R. d. S. (2010). Shape retrieval using contour features and distance optmization. In VISAPP, volume 1, pages 197 – 202.

Pedronette, D. C. G. and Torres, R. d. S. (2012). Exploiting pairwise recommendation and clustering strategies for image re-ranking. Information Sciences, 207:19–34.

Pedronette, D. C. G. and Torres, R. d. S. (2013). Image re-ranking and rank aggregation based on similarity of ranked lists. Pattern Recognition, 46(8):2350–2360.

Pedronette, D. C. G., Torres, R. d. S., Borin, E., and Breternitz, M. (2012). Efficient image re-ranking computation on GPUs. In ISPA.

Pedronette, D. C. G., Torres, R. d. S., Borin, E., and Breternitz, M. (2013). RL-Sim algorithm acceleration on GPUs. In SBAC.

Pedronette, D. C. G. a., Almeida, J., and Torres, R. D. S. (2014). A scalable re-ranking method for contentbased image retrieval. Information Sciences, 265:91–104.

Stehling, R. O., Nascimento, M. A., and Falcão, A. X. (2002). A compact and efficient image retrieval approach based on border/interior pixel classification. In CIKM, pages 102–109.

Swain, M. J. and Ballard, D. H. (1991). Color indexing. International Journal on Computer Vision, 7(1):11–32.

Tao, B. and Dickinson, B. W. (2000). Texture recognition and image retrieval using gradient indexing. JVCIR, 11(3):327–342.

Torres, R. d. S. and Falc˜ao, A. X. (2007). Contour Salience Descriptors for Effective Image Retrieval and Analysis. Image and Vision Computing, 25(1):3–13.

Valem, L. P., Pedronette, D. C. G., Torres, R. d. S., Borin, E., and Almeida, J. (2015). Effective, efficient, and scalable unsupervised distance learning in image retrieval tasks. ICMR.

van de Weijer, J. and Schmid, C. (2006). Coloring local feature extraction. In ECCV, pages 334–348.

Yang, X., Koknar-Tezel, S., and Latecki, L. J. (2009). Locally constrained diffusion process on locally densified distance spaces with applications to shape retrieval. In CVPR, pages 357–364.

Yang, X., Prasad, L., and Latecki, L. (2013). Affinity learning with diffusion on tensor product graph. IEEE Transactions on Pattern Analysis and Machine Intelligence,, 35(1):28–38.

Zagoris, K., Chatzichristofis, S., Papamarkos, N., and Boutalis, Y. (2010). Automatic image annotation and retrieval using the joint composite descriptor. In PCI, pages 143–147.
Publicado
20/07/2015
VALEM, Lucas; PEDRONETTE, Daniel. Eficácia, Eficiência e Escalabilidade em Método de Aprendizado Não Supervisionado de Busca de Imagens. In: CONCURSO DE TRABALHOS DE INICIAÇÃO CIENTÍFICA DA SBC (CTIC-SBC), 34. , 2015, Recife. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2015 . p. 61-70.