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.
Chapter PDF
References
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)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. Journal of Computer Vision 60(2), 91–110 (2004)
Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 27(10), 1615–1630 (2005)
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)
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)
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)
Griffin, G., Perona, P.: Learning and using taxonomies for fast visual categorization. In: CVPR 2008. IEEE Computer Society (2008)
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)
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)
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)
Vidal-Naquet, M., Ullman, S.: Object recognition with informative features and linear classification. In: ICCV, Nice, France, pp. 281–288 (2003)
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)
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)
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)
Todorovic, S., Ahuja, N.: Unsupervised category modeling, recognition, and segmentation in images. IEEE Trans. Pattern Anal. Mach. Intell. 30(12), 2158–2174 (2008)
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)
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)
Malisiewicz, T., Efros, A.A.: Improving spatial support for objects via multiple segmentations. In: British Machine Vision Conference, BMVC (September 2007)
Carreira, J., Sminchisescu, C.: CPMC: Automatic object segmentation using constrained parametric min-cuts. IEEE Trans. Pattern Anal. Mach. Intell. (2012)
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)
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)
Ahuja, N., Todorovic, S.: Connected segmentation tree - a joint representation of region layout and hierarchy. In: CVPR 2008. IEEE Computer Society (2008)
Malisiewicz, T., Efros, A.A.: Improving spatial support for objects via multiple segmentations. In: British Machine Vision Conference, BMVC (September 2007)
Mumford, D.: Elastica and computer vision. In: Algebraic Geometry and Its Applications, pp. 491–506. Springer (1994)
Williams, L., Jacobs, D.: Stochastic completion fields: A neural model of illusory contour shape and salience. Neural Computation 9, 849–870 (1997)
Kimia, B.B., Frankel, I., Popescu, A.M.: Euler spiral for shape completion. IJCV 54, 159–182 (2003)
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)
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)
Giblin, P.J., Kimia, B.B.: On the intrinsic reconstruction of shape from its symmetries. PAMI 25(7), 895–911 (2003)
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)
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)
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)
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)
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)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Narayanan, M., Kimia, B. (2012). Bottom-Up Perceptual Organization of Images into Object Part Hypotheses. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds) Computer Vision – ECCV 2012. ECCV 2012. Lecture Notes in Computer Science, vol 7572. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33718-5_19
Download citation
DOI: https://doi.org/10.1007/978-3-642-33718-5_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33717-8
Online ISBN: 978-3-642-33718-5
eBook Packages: Computer ScienceComputer Science (R0)