Robust matching and hierarchical recognition of 2-D shapes using “Chain of Circles”
Based on a resulting medial axis configuration of 2-D shapes, previously we proposed a new shape description called Chain of Circles (CoCs). This paper shows how the CoCs representation is robustly used in matching of shapes with various deformations. The shape dissimilarity between a pair of CoCs is first coarsely calculated via the matching process, then finely calculated between specific and salient parts of the shapes, and finally used for recognition. This hierarchical recognition scheme seems to be in accord with the human shape recognition and gives much computational efficiency.
Unable to display preview. Download preview PDF.
- 1.Jae-Moon Chung and Noboru Ohnishi, “Chain of circles for matching and recognition of planar shapes,” Technical Report of IEICE, vol. IE96-126, pp. 23–30, Feb. 1997, and Proc. IJCAI-97, pp.1482–1487.Google Scholar
- 2.H. Blum, “A transformation for extracting new descriptors of shape,” In W. Wathen-Dunn, editor, Models for perception of speech and visual form, MIT Press, 1967.Google Scholar