Detecting Instances of Shape Classes That Exhibit Variable Structure
This paper proposes a method for detecting shapes of variable structure in images with clutter. The term “variable structure” means that some shape parts can be repeated an arbitrary number of times, some parts can be optional, and some parts can have several alternative appearances. The particular variation of the shape structure that occurs in a given image is not known a priori. Existing computer vision methods, including deformable model methods, were not designed to detect shapes of variable structure; they may only be used to detect shapes that can be decomposed into a fixed, a priori known, number of parts. The proposed method can handle both variations in shape structure and variations in the appearance of individual shape parts. A new class of shape models is introduced, called Hidden State Shape Models, that can naturally represent shapes of variable structure. A detection algorithm is described that finds instances of such shapes in images with large amounts of clutter by finding globally optimal correspondences between image features and shape models. Experiments with real images demonstrate that our method can localize plant branches that consist of an a priori unknown number of leaves and can detect hands more accurately than a hand detector based on the chamfer distance.
KeywordsHide Markov Model Edge Pixel Viterbi Algorithm Shape Part Active Shape Model
Unable to display preview. Download preview PDF.
- 2.Sebastian, T.B., Klein, P.N., Kimia, B.B.: Recognition of shapes by editing shock graphs. In: ICCV, pp. 755–762 (2001)Google Scholar
- 5.Cootes, T.F., Taylor, C.J., Cooper, D.H., Graham, J.: Active shape models - their training and application. CVIU 61, 38–59 (1995)Google Scholar
- 7.Sigal, L., Isard, M., Sigelman, B.H., Black, M.J.: Attractive people: Assembling loose-limbed models using non-parametric belief propagation. In: NIPS (2003)Google Scholar
- 8.Zhang, J., Collins, R., Liu, Y.: Representation and matching of articulated shapes. In: CVPR, vol. 2, pp. 342–349 (2004)Google Scholar
- 11.Felzenszwalb, P.F.: Representation and Detection of Shapes in Images. PhD thesis, MIT (2003)Google Scholar
- 15.Arica, N., Yarman-Vural, F.T.: A shape descriptor based on circular Hidden Markov Model. In: ICPR, pp. 1924–1927 (2000)Google Scholar
- 18.Han, F., Zhu, S.C.: Bottom-up/top-down image parsing by attribute graph grammar. In: ICCV, pp. 1778–1785 (2005)Google Scholar
- 21.Barrow, H.G., Tenenbaum, J.M., Bolles, R.C., Wolf, H.C.: Parametric correspondence and chamfer matching: Two new techniques for image matching. In: IJCAI, pp. 659–663 (1977)Google Scholar
- 22.Thayananthan, A., Stenger, B., Torr, P.H.S., Cipolla, R.: Shape context and chamfer matching in cluttered scenes. In: CVPR, pp. 127–133 (2003)Google Scholar