Abstract
A qualitative, volumetric part-based model is proposed to improve the categorical invariance and viewpoint invariance in content-based image retrieval, and a novel two-step part-categorization method is presented to build it. The method consists first in transforming parts extracted from a segmented contour primitive map and then categorizing the transformed parts using interpretation rules. The first step allows noisy extracted parts to be transformed to the domain of a simple classifier. The second step computes features of the transformed parts for categorization. Content-based image retrieval experiments using real images of complex multi-part objects confirm that a model built from the categorized parts improves both the categorical invariance and the viewpoint invariance. It does so by directly addressing the fundamental limits of low-level models.
References
Bergevin R. and Levine M.D. (1993). Generic object recognition: building and matching coarse descriptions from line drawings. IEEE Trans. Pattern Anal. Mach. Intell. 15(1): 19–36
Bernier, J.-F., Bergevin, R.: Generic detection of multi-part objects. In: 18th International Conference on Pattern Recognition, Hong Kong, China, August 2006
Biederman I. (1985). Human image understanding: recent research and a theory. Comput. Vision Graphics Image Process. 32: 29–73
Bilodeau, G.-A., Bergevin, R.: Generic modeling of 3D objects from single 2D images. In: IAPR 15th International Conference on Pattern Recognition, pp. 770–773. Barcelona, Spain (2000)
Bilodeau G.-A. and Bergevin R. (2002). Part segmentation of objects in real images. Pattern Recognition 35(12): 2913–2926
Bilodeau G.-A. and Bergevin R. (2005). Matching graphs with fuzzy attributes in machine vision. Acta Press Int. J. Robot. Automat. 20(1): 50–59
Dhillon, I., Fan, J., Guan, Y.: Efficient clustering of very large document collections. In: Grossman, R., Kamath, G., Naburu, R. (eds.) Data Mining for Scientific and Engineering Applications, pp. 15–16. Kluwer Academic Publishers (2001)
Dickinson S.J., Pentland A.P. and Rosenfeld A. (1992). 3-D Shape recovery using distributed aspect matching. IEEE Trans. Pattern Anal. Mach. Intell. 14(2): 174–198
Dickinson, S.J., Pentland, A.P., Stevenson, S.: Viewpoint-invariant indexing for content-based image retrieval. In: IEEE International Workshop on Content-based Access of Image and Video Databases, pp. 20–30. Bombay, India (1998)
Dorko, G., Schmid, C.: Selection of scale-invariant parts for object class recognition. In: Proceedings of the Ninth International Conference on Computer Vision (ICCV’03), pp. 20–30. Nice, France (2003)
Elder, J. H., Zucker, S.W.: Computing contour closure. In: Proceedings of the 4th European Conference on Computer Vision, pp. 399–411. Cambridge, England (1996)
Forsyth, D.A., Ioffe, S., Haddon, J.: Finding objects by grouping primitives. In: Conf. Rec. of 32nd Asilomar Conference on Signals, Systems & Computers, pp. 905–909. Pacific Grove, CA (1998)
Gross A.D. and Boult T. E. (1996). Recovery of SHGCs from a single intensity view. IEEE Trans. Pattern Anal. Mach. Intell. 18(2): 161–180
Hérault L. and Horaud R. (1993). Figure-Ground Discrimination: A Combinatorial Optimization Approach. IEEE Trans. Pattern Anal. Mach. Intell. 15(9): 899–914
Jacobs D.W. (1996). Robust and Efficient Detection of Salient Convex Groups. IEEE Trans. Pattern Anal. Mach. Intell. 18(1): 23–37
Jacot-Descombes A. and Pun T. (1997). Asynchronous Perceptual Grouping: From Contours to Relevant 2-D Structures. Comput. Vision Image Understand 66(1): 1–24
Liu, J., Mundy, J., Forsyth, D., Zisserman, A., Rothwell, C.: Efficient Recognition of Rotationally symmetric surfaces and straight homogenous generalized cylinders. In: Proceedings of the IEEE Computer Vision and Pattern Recognition, pp. 123–128. New York, NY (1993)
Liu, W., Zhang, C., Yuan, B.: Superquadric-based reconstruction from 2D images. In: Proceedings of the 6th International Conference on Signal Processing, Beijing, China, August 26–30, 2002, pp. 668–671
Martin D., Fowlkes C. and Malik J. (2004). Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE Trans. Pattern Anal. Mach. Intell. 26(5): 530–549
Mokhtari, M., Bergevin R.: Generic multi-scale segmentation and curve approximation method. In: Procedings of LNCS 2106: Scale-Space and Morphology in Computer Vision, Third Int. Conf., pp. 227–235. Vancouver, Canada (2001)
Mokhtarian, F.: Silhouette-based object recognition with occlusion through curvature scale-space. In: Proceedings of the 4th European Conference on Computer Vision, pp. 566–578. Cambridge, England (1996)
Nishida H. (2002). Structural feature indexing for retrieval of partially visible shapes. Pattern Recognition 35(1): 55–67
Pilu, M., Fisher, R.B.: Recognition of geons by parametric deformable contour models. In: Proceedings of the European Conference of Computer Vision, Cambridge, England, in Lecture Notes in Computer Science, LNCS 1064, pp. 71–92. Springer, Berlin Heidelberg New York, April 1996
Ponce J., Chelberg D. and Mann W.B. (1989). Invariant properties of straight homogenous generalized cylinders and their contours. IEEE Trans. Pattern Anal. Mach. Intell. 11(9): 951–966
Randrianarisoa, V., Bernier, J.-F., Bergevin, R.: Detection of multi-part objects by top-down perceptual grouping. In: Proceedings 2nd Canadian Conference on Computer and Robot Vision, pp. 536–543. Victoria, Canada (2005)
Sato H. and Binford T.O. (1993). Finding and recovering SHGC objects in an edge image. CVGIP: Image Understand. 57(3): 346–358
Schaffalitzky, F., Zisserman, A.: Multi-view matching for unordered image sets, or “How do I organize my holiday snaps?” In: Proceedings of the 7th European Conference on Computer Vision, pp. 414–431. Copenhagen, Denmark (2002)
Selinger A. and Nelson R.C. (1999). A perceptual grouping hierarchy for appearance-based 3D object recognition. Comput. Vision Image Understand. 76(1): 83–92
Siddiqi K., Shokoufandeh A., Dickinson S.J. and Zucker S.W. (1999). Shock graphs and shape matching. Int. J. Comput Vision 35(1): 13–32
Singh, S., Seyranian, G.D., Hoffman, D.D.: Parsing Silhouettes. Percept. Psychophys. (61), 636–660 (1999)
Sivic, J., Zisserman, A.: Video Google: a text retrieval approach to object matching in videos. In: Proceedings of the Ninth IEEE International Conference on Computer Vision, pp. 1470–1477. Nice, France (2003)
Squire D.M., Müller W., Müller H. and Pun T. (2000). Content-based query of image databases: inspirations from text retrieval. Pattern Recognition Lett. 21: 1193–1198
Stein F. and Medioni G. (1992). Structural Indexing: Efficient 2D Object Recognition. IEEE Trans. Pattern Anal. Mach. Intell. 14(12): 1198–1204
Zerroug M. and Nevatia R. (1999). Part-based 3D description of complex objects from a single image. IEEE Trans. Pattern Anal. Mach. Intell. 21(9): 835–848
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Bilodeau, GA., Bergevin, R. Qualitative part-based models in content-based image retrieval. Machine Vision and Applications 18, 275–287 (2007). https://doi.org/10.1007/s00138-006-0057-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-006-0057-8