Advertisement

Bottom-Up Perceptual Organization of Images into Object Part Hypotheses

  • Maruthi Narayanan
  • Benjamin Kimia
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7572)

Abstract

The demise of “segmentation-then-recognition” strategy led to a paradigm shift toward feature-based discriminative recognition with significant success. However, increased complexity in multi-class datasets reveals that local low-level features may not be sufficiently discriminative, requiring the construction and use of more complex structural features which are necessarily category independent. The paper proposes a bottom-up procedure for generating fragment features which are intended to be object part hypotheses. Suggesting that the demise of segmentation to generate a representation suitable for recognition was due to prematurely committing to a grouping option in the face of ambiguities, the proposed framework considers and tracks multiple alternate grouping options. This approach is made tractable by (i) using a medial fragment representation which allows for the simultaneous use of multiple cues, (ii) a set of transforms to effect grouping operations, (iii) a containment graph representation which avoids duplicate consideration of possibilities, and the estimation of the likelihood of a grouping sequence to retain only plausible groupings. The resulting hypotheses are evaluated intrinsically by measuring their ability to represent objects with a few fragments. They are also evaluated by comparison to algorithms which aim to generate full object segments, with results that match or exceed the state of art, thus demonstrating the suitability of the proposed mid-level representation.

Keywords

IEEE Computer Society Illusory Contour Object Part Good Continuation British Machine Vision 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Gool, L.J.V.: A comparison of affine region detectors. IJCV 65(1-2), 43–72 (2005)CrossRefGoogle Scholar
  2. 2.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. Journal of Computer Vision 60(2), 91–110 (2004)CrossRefGoogle Scholar
  3. 3.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 27(10), 1615–1630 (2005)CrossRefGoogle Scholar
  4. 4.
    Felzenszwalb, P.F., Girshick, R.B., McAllester, D.A., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627–1645 (2010)CrossRefGoogle Scholar
  5. 5.
    Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Miami, Florida, USA. IEEE Computer Society Press (2009)Google Scholar
  6. 6.
    Fink, M., Ullman, S.: From Aardvark to Zorro: A benchmark for mammal image classification. International Journal of Computer Vision 77(1-3), 143–156 (2008)CrossRefGoogle Scholar
  7. 7.
    Griffin, G., Perona, P.: Learning and using taxonomies for fast visual categorization. In: CVPR 2008. IEEE Computer Society (2008)Google Scholar
  8. 8.
    Deng, J., Berg, A.C., Li, K., Fei-Fei, L.: What Does Classifying More Than 10,000 Image Categories Tell Us? In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 71–84. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  9. 9.
    Tatu, A., Lauze, F., Nielsen, M., Kimia, B.B.: Exploring the representation capabilities of the HOG descriptor. In: ICCV Workshops, pp. 1410–1417. IEEE (2011)Google Scholar
  10. 10.
    Dickinson, S.: The evolution of object categorization and the challenge of image abstraction. In: Dickinson, S., Leonardis, A., Schiele, B., Tarr, M. (eds.) Object Categorization: Computer and Human Vision Perspectives, pp. 1–37. Cambridge University Press (2009)Google Scholar
  11. 11.
    Vidal-Naquet, M., Ullman, S.: Object recognition with informative features and linear classification. In: ICCV, Nice, France, pp. 281–288 (2003)Google Scholar
  12. 12.
    Tamrakar, A., Kimia, B.B.: Medial visual fragments as an intermediate image representation for segmentation and perceptual grouping. In: Proceedings of CVPR Workshop on Perceptual Organization in Computer Vision, p. 47 (2004)Google Scholar
  13. 13.
    Hoiem, D., Efros, A.A., Hebert, M.: Geometric context from a single image. In: ICCV 2005: Proceedings of the Tenth IEEE International Conference on Computer Vision, pp. 654–661. IEEE Computer Society (October 2005)Google Scholar
  14. 14.
    Todorovic, S., Ahuja, N.: Extracting subimages of an unknown category from a set of images. In: CVPR 2006, pp. 927–934. IEEE Computer Society (2006)Google Scholar
  15. 15.
    Todorovic, S., Ahuja, N.: Unsupervised category modeling, recognition, and segmentation in images. IEEE Trans. Pattern Anal. Mach. Intell. 30(12), 2158–2174 (2008)CrossRefGoogle Scholar
  16. 16.
    Arbelaez, P., Maire, M., Fowlkes, C.C., Malik, J.: From contours to regions: An empirical evaluation. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Miami, Florida, USA, pp. 2294–2301. IEEE Computer Society Press (2009)Google Scholar
  17. 17.
    Ozcanli, O.C., Kimia, B.B.: Generic object recognition via shock patch fragments. In: Rajpoot, N.M., Bhalerao, A. (eds.) Proceedings of the British Machine Vision Conference, September 10-13, pp. 1030–1039. Warwick Print, Coventry (2007)Google Scholar
  18. 18.
    Malisiewicz, T., Efros, A.A.: Improving spatial support for objects via multiple segmentations. In: British Machine Vision Conference, BMVC (September 2007)Google Scholar
  19. 19.
    Carreira, J., Sminchisescu, C.: CPMC: Automatic object segmentation using constrained parametric min-cuts. IEEE Trans. Pattern Anal. Mach. Intell. (2012)Google Scholar
  20. 20.
    Endres, I., Hoiem, D.: Category Independent Object Proposals. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 575–588. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  21. 21.
    Ren, X., Malik, J.: Learning a classification model for segmentation. In: ICCV 2003: Proceedings of the Ninth IEEE International Conference on Computer Vision, pp. 10–17. IEEE Computer Society (2003)Google Scholar
  22. 22.
    Ahuja, N., Todorovic, S.: Connected segmentation tree - a joint representation of region layout and hierarchy. In: CVPR 2008. IEEE Computer Society (2008)Google Scholar
  23. 23.
    Malisiewicz, T., Efros, A.A.: Improving spatial support for objects via multiple segmentations. In: British Machine Vision Conference, BMVC (September 2007)Google Scholar
  24. 24.
    Mumford, D.: Elastica and computer vision. In: Algebraic Geometry and Its Applications, pp. 491–506. Springer (1994)Google Scholar
  25. 25.
    Williams, L., Jacobs, D.: Stochastic completion fields: A neural model of illusory contour shape and salience. Neural Computation 9, 849–870 (1997)Google Scholar
  26. 26.
    Kimia, B.B., Frankel, I., Popescu, A.M.: Euler spiral for shape completion. IJCV 54, 159–182 (2003)zbMATHCrossRefGoogle Scholar
  27. 27.
    Kimia, B.B., Tannenbaum, A.R., Zucker, S.W.: Toward a Computational Theory of Shape: An Overview. In: Faugeras, O. (ed.) ECCV 1990. LNCS, vol. 427, pp. 402–407. Springer, Heidelberg (1990)CrossRefGoogle Scholar
  28. 28.
    Kimia, B.B., Tannenbaum, A.R., Zucker, S.W.: Shapes, shocks, and deformations, I: The components of shape and the reaction-diffusion space. IJCV 15(3), 189–224 (1995)CrossRefGoogle Scholar
  29. 29.
    Giblin, P.J., Kimia, B.B.: On the intrinsic reconstruction of shape from its symmetries. PAMI 25(7), 895–911 (2003)CrossRefGoogle Scholar
  30. 30.
    Geisler, W.S., Perry, J.S., Super, B.J., Gallogly, D.P.: Edge co-occurrence in natural images predicts contour grouping performance. Vision Research 41, 711–724 (2001)CrossRefGoogle Scholar
  31. 31.
    Narayanan, M., Kimia, B.: To complete or not to complete: Gap completion in real images. In: 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 47–54 (June 2012)Google Scholar
  32. 32.
    Alpert, S., Galun, M., Basri, R., Brandt, A.: Image segmentation by probabilistic bottom-up aggregation and cue integration. In: CVPR 2007. IEEE Computer Society (2007)Google Scholar
  33. 33.
    Maire, M., Arbelaez, P., Fowlkes, C., Malik, J.: Using contours to detect and localize junctions in natural images. In: CVPR 2008, pp. 1–8. IEEE Computer Society (2008)Google Scholar
  34. 34.
    Tamrakar, A., Kimia, B.B.: No grouping left behind: From edges to curve fragments. In: ICCV 2007: Proceedings of the Eleventh IEEE International Conference on Computer Vision, Rio de Janeiro, Brazil. IEEE Computer Society (October 2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Maruthi Narayanan
    • 1
  • Benjamin Kimia
    • 1
  1. 1.School of EngineeringBrown UniversityProvidenceUSA

Personalised recommendations