Heuristic strategy for feature matching in parallel curve detection

Feature matching has been proved very efficient as an approach for curve matching. However, when there are lots of features detected in the two curves, the possible combinations of matching among these features are prohibitive computationally. In this paper, we propose a heuristic algorithm to select the most promising coupling schemes out of these possible patterns. For parallel curve detection, the rationales we employed include proximity measure and compatibility between tangent orientations at these feature points.

[1]  Horace Ho-Shing Ip,et al.  On the Detection of Parallel Curves Models and Representations , 1996, Int. J. Pattern Recognit. Artif. Intell..

[2]  Tomaso Poggio,et al.  Cooperative computation of stereo disparity , 1988 .

[3]  F. Ulupinar,et al.  Inferring shape from contour for curved surfaces , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[4]  Micha Sharir,et al.  Identification of Partially Obscured Objects in Two and Three Dimensions by Matching Noisy Characteristic Curves , 1987 .

[5]  A. Witkin,et al.  On the Role of Structure in Vision , 1983 .

[6]  Gérard G. Medioni,et al.  Hierarchical Decomposition and Axial Shape Description , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Haim J. Wolfson.  On curve matching , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Mandyam D. Srinath,et al.  Invariant planar shape recognition using dynamic alignment , 1987, ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing.