Contour Extraction Based on Deformable Model and Dynamic Programming

DOI

10.2991/icmemtc-16.2016.25How to use a DOI?

Keywords

deformable model; region of interest; dynamic programming; contour extraction

Abstract

In this paper, a new model for extraction of active contours of the quasi-circular targets in a given image which is based on edge detection and dynamic programming(DP) is proposed. In order to guarantee the detected closed contour approximating to the real contour of the target as well as possible, the DP algorithm was launched as the probability distribution of the polar image's edge is obtained by which the computational time was significantly reduced. By the utilization of the image intensity information and the balloon force, the external force in the energy-minimizing function of deformable model is synthetically designed. The theoretical analysis and experiment results demonstrated that the capability of searching a continuous and closed edge contour with the proposed method was remarkably extended compared to the other two methods.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Cheng Zhao
PY  - 2016/04
DA  - 2016/04
TI  - Contour Extraction Based on Deformable Model and Dynamic Programming
BT  - Proceedings of the 2016 3rd International Conference on Materials Engineering, Manufacturing Technology and Control
PB  - Atlantis Press
SP  - 132
EP  - 135
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmemtc-16.2016.25
DO  - 10.2991/icmemtc-16.2016.25
ID  - Zhao2016/04
ER  -