2D cross entropy method for image segmentation based on artificial bee colony optimization

DOI

10.2991/isaeece-16.2016.56How to use a DOI?

Keywords

image segmentation, two-dimensional cross entropy, artificial bee colony algorithm

Abstract

A kind of image segmentation method with two-dimensional cross entropy was proposed based on the artificial bee colony algorithm to overcome the large amount of calculation and long computing time. Firstly, the principle of two-dimensional cross entropy threshold segmentation was analyzed. Then, the bionic mechanism and searching optimization process of the artificial bee colony algorithm were analyzed, and the threshold segmentation method of two-dimensional cross entropy combined with artificial bee colony algorithm was proposed. Finally, typical image segmentation experiments by using the proposed method were performed and the results were compared with two-dimensional cross entropy exhaustive segmentation method and two-dimensional entropy segmentation method based on Particle Swarm Optimization (PSO). Experimental results show that the speed of the proposed method is ten times faster than the two-dimensional entropy exhaustive segmentation method respectively. Moreover, the threshold selection accuracy and running speed of the proposed method are both better than the threshold segmentation method of two-dimensional cross entropy based on PSO. Therefore, the image segmentation method of two-dimensional cross entropy based on artificial bee colony algorithm can quickly and efficiently resolve image segmentation problems.

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  - Xianglan Ye
AU  - Tianhuang Chen
PY  - 2016/04
DA  - 2016/04
TI  - 2D cross entropy method for image segmentation based on artificial bee colony optimization
BT  - Proceedings of the 2016 International Symposium on Advances in Electrical, Electronics and Computer Engineering
PB  - Atlantis Press
SP  - 295
EP  - 298
SN  - 2352-5401
UR  - https://doi.org/10.2991/isaeece-16.2016.56
DO  - 10.2991/isaeece-16.2016.56
ID  - Ye2016/04
ER  -