Contour shape description based on an arch height function

Abstract A new method to extract contour features is proposed. For any contour C , a function, which we call Arch Height Function (AHF), is defined for each point and its value on C is computed. The set of AHF values is then used as a description of the shape of C . In particular, its local maxima, if they exist, correspond precisely to the cornerpoints of C . Besides, the method is computationally efficient as compared with the existing techniques of the contour feature extraction. The new method provides an effective and reliable tool for contour description, especially for angle detection. Some experimental results that demonstrate the adaptability and reliability of the AHF method are presented.

[1]  Herbert Freeman,et al.  On the Encoding of Arbitrary Geometric Configurations , 1961, IRE Trans. Electron. Comput..

[2]  Ramakant Nevatia,et al.  Description and Recognition of Curved Objects , 1977, Artif. Intell..

[3]  Larry S. Davis,et al.  A Corner-Finding Algorithm for Chain-Coded Curves , 1977, IEEE Transactions on Computers.

[4]  Dana H. Ballard,et al.  Computer Vision , 1982 .

[5]  Fang-Hsuan Cheng,et al.  Parallel algorithm for corner finding on digital curves , 1988, Pattern Recognit. Lett..

[6]  K. Ramesh Babu,et al.  Linear Feature Extraction and Description , 1979, IJCAI.

[7]  Benjamin Bell,et al.  Contour Tracking and Corner Detection in a Logic Programming Environment , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  J. Y. Yang,et al.  Matching Perspective Views of a Polyhedron Using Circuits , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Min-Hong Han,et al.  Identification of cornerpoints of two-dimensional images using a line search method , 1989, Pattern Recognit..