Curve Extraction Using Minimal Path Propagation Backtracking and Hough Transform

IJCSEC Front Page

This paper proposes an approach termed minimal path propagation with backtracking and hough transform. It was found that the information in the process of backtracking from reached points can be well utilized to overcome the problems faced in existing methods and improve the extraction performance. The whole algorithm is robust to parameter setting and allows a coarse setting of the starting point. Minimal path techniques can absolutely delineate geometrically curve-like structures by finding the path with minimal accumulated cost between the endpoints. Curve extraction have found wide practical applications such as line identification, crack detection, and vascular centerline extraction.

Keywords: Curve-like structure, hough transform, centerline, minimal path tracking, backtracking, endpoint problem, shortcut problem, accumulation problem.


  1. L. D. Cohen and R. Kimmel, “Global minimum for active contour models: A minimal path approach ,” Int. J. Comput. Vis., vol. 24, no. 1,pp. 57–78, Aug. 1997.
  2. Y. Rouchdy and L. D. Cohen, “Geodesic voting methods: Overview, extensions and application to blood vessel segmentation,” Comput.Methods Biomech. Biomed. Eng., Imag. Visualizat., vol. 1, no. 2,pp. 79–88, Mar. 2013.
  3. V. Kaul, A. Yezzi, and Y. C. Tsai, “Detecting curves with unknown endpoints and arbitrary topology using minimal paths,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 34, no. 10, pp. 1952–1965, Oct. 2012.
  4. Yang Chen and Yudong Zhang, “Curve-Like Structure Extraction Using Minimal Path Propagation With Backtracking,” IEEE Trans. Image Processing., vol. 25, no. 2,pp.988-1003, Feb. 2016.