Abstract.
This paper proposes an efficient window-based semi-automatic feature extraction technique which uses simulated annealing for minimizing the energy of an active contour within a specified image region. The energy is computed based on a chamfer image, in which pixel values are a function of distance to image edges. A user places a number of control points close to the feature of interest. B-spline fitted to these points provides an initial approximation of the contour. A window containing both the initial contour and the feature of interest is considered. The contour with minimum energy inside the window provides the final delineation. Comparison of the performance of the proposed algorithm with traditional snake, a popular feature extraction technique based on energy minimization, demonstrates the superiority of the SAFE technique.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
Author information
Authors and Affiliations
Additional information
Received 18 August 1999 / Revised 25 October 2000 / Accepted in revised form 8 December 2000
Rights and permissions
About this article
Cite this article
Maulik, U., Bandyopadhyay, S. & Trinder, J. SAFE: An Efficient Feature Extraction Technique. Knowledge and Information Systems 3, 374–387 (2001). https://doi.org/10.1007/PL00011674
Issue Date:
DOI: https://doi.org/10.1007/PL00011674