Abstract
We describe a new approach for learning to perform class-based segmentation using only unsegmented training examples. As in previous methods, we first use training images to extract fragments that contain common object parts. We then show how these parts can be segmented into their figure and ground regions in an automatic learning process. This is in contrast with previous approaches, which required complete manual segmentation of the objects in the training examples. The figure-ground learning combines top-down and bottom-up processes and proceeds in two stages, an initial approximation followed by iterative refinement. The initial approximation produces figure-ground labeling of individual image fragments using the unsegmented training images. It is based on the fact that on average, points inside the object are covered by more fragments than points outside it. The initial labeling is then improved by an iterative refinement process, which converges in up to three steps. At each step, the figure-ground labeling of individual fragments produces a segmentation of complete objects in the training images, which in turn induce a refined figure-ground labeling of the individual fragments. In this manner, we obtain a scheme that starts from unsegmented training images, learns the figure-ground labeling of image fragments, and then uses this labeling to segment novel images. Our experiments demonstrate that the learned segmentation achieves the same level of accuracy as methods using manual segmentation of training images, producing an automatic and robust top-down segmentation.
Chapter PDF
Similar content being viewed by others
References
Needham, A., Baillargeon, R.: Effects of prior experience in 4.5-month-old infants’ object segregation. Infant Behaviour and Development 21, 1–24 (1998)
Peterson, M., Gibson, B.: Shape recognition contributions to figure-ground organization in three-dimensional displays. Cognitive Psychology 25, 383–429 (1993)
Sali, E., Ullman, S.: Detecting object classes by the detection of overlapping 2-d fragments. In: BMVC, 10th, pp. 203–213 (1999)
Weber, M., Welling, M., Perona, P.: In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1842, pp. 18–32. Springer, Heidelberg (2000)
Agarwal, S., Roth, D.: Learning a sparse representation for object detection. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 113–130. Springer, Heidelberg (2002)
Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: CVPR, vol. II, pp. 264–271 (2003)
Borenstein, E., Ullman, S.: Class-specific, top-down segmentation. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2351, pp. 109–124. Springer, Heidelberg (2002)
Ullman, S., Sali, E., Vidal-Naquet, M.: A fragment based approach to object representation and classification. In: Arcelli, C., Cordella, L.P., Sanniti di Baja, G. (eds.) IWVF 2001. LNCS, vol. 2059, pp. 85–100. Springer, Heidelberg (2001)
Sharon, E., Brandt, A., Basri, R.: Segmentation and boundary detection using multiscale intensity measurements. In: CVPR, Hawaii, vol. I, pp. 469–476 (2001)
Yuille, A., Hallinan, P.: Deformable templates. In: Blake, A., Yuille, A. (eds.) Active Vision, pp. 21–38. MIT press, Cambridge (1992)
Cootes, T., Taylor, C., Cooper, D., Graham, J.: Active shape models — their training and application. CVIU 61, 38–59 (1995)
Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active contour models. International Journal of Computer Vision 1, 321–331 (1987)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Borenstein, E., Ullman, S. (2004). Learning to Segment. In: Pajdla, T., Matas, J. (eds) Computer Vision - ECCV 2004. ECCV 2004. Lecture Notes in Computer Science, vol 3023. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24672-5_25
Download citation
DOI: https://doi.org/10.1007/978-3-540-24672-5_25
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21982-8
Online ISBN: 978-3-540-24672-5
eBook Packages: Springer Book Archive