Acquisition of 2-D shape models from scenes with overlapping objects using string matching
In this paper we describe a system that is able to acquire models of 2-D shapes from cluttered scenes. The input of the system is a sequence of images each of which shows an unknown number of overlapping unknown 2-D objects. The system identifies matching partial shapes across different images and combines them into complete 2-D shape models thus giving a complete interpretation of the input scenes. The identification of partial shapes is based on string matching, whereas a graph search procedure is used for shape model generation. The system has been fully implemented and tested on images containing parts of a jigsaw puzzle.
Unable to display preview. Download preview PDF.
- J.L. Turne, T.N. Mudge, R.A. Volz, Recognizing Partially Occluded Parts, IEEE Trans. Pattern Anal. Mach. Intell., Vol.7, No.4, 1985, pp. 410–421Google Scholar
- W.E.L. Grimson and T. Lonyano-Perez, Localizing Overlapping Parts by Searching the Interpretation Tree, IEEE Transc. Pattern Anal. Mach. Intell., Vol.9, No.4, 1987, pp. 469–482Google Scholar
- N. Ayache, O.D. Faugeras, HYPER: a New Approach for the Recognition and Positioning of two-dimensional Objects, IEEE Trans. Pattern Anal. Mach. Intell., Vol.8, No.1, 1986, pp. 44–54Google Scholar
- Y.-T. Tsay, W.-H. Tsai, Model-guided Attributed String Matching by Split-and-merge for Shape Recognition, Int. J. Pattern Recognition Artif. Intell. No.3, 1989, pp. 159–179Google Scholar
- H.J. Wolfson, Model-based Object Recognition by Geometric Hashing, Proc. 1st Eur. Conf. Comput. Vision Antibes, 1990, pp. 526–536Google Scholar
- K.Y. Kupeev, H.J. Wolfson, A New Method of Estimating Shape Similarity, Pattern Recognition Letters, No.17, 1996, pp. 873–887Google Scholar
- A. Hutchinson, Algorithmic Learning, Oxford University Press, 1994Google Scholar
- J.W. Shavlick, T.G. Dietterich (eds.), Readings in Machine Learning, Morgan Kaufman, San Mateo, 1990Google Scholar
- B. Bhanu, T. Poggio (guest eds.), Special Section on Learning in Computer Vision, IEEE Trans. Pattern Anal. Mach. Intell., Vol.16, No.9, 1994, pp. 865–919Google Scholar