Open AccessMaximum Entropy Image Segmentation Method Based On Improved Firefly Algorithm
Author(s) -
Qianru Liu,
Zhanjun Jiang,
Haoqiang Shi
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1213/3/032023
Subject(s) - firefly algorithm , image segmentation , entropy (arrow of time) , segmentation , firefly protocol , algorithm , computer science , region growing , segmentation based object categorization , parametric statistics , scale space segmentation , artificial intelligence , mathematics , principle of maximum entropy , pattern recognition (psychology) , statistics , particle swarm optimization , zoology , physics , quantum mechanics , biology
An adaptive parametric firefly algorithm is proposed for the premature convergence of the firefly algorithm itself and the late oscillation of the algorithm iteration. In the image threshold segmentation test experiment, the algorithm is used to optimize the maximum entropy image segmentation, and the maximum entropy and the basic firefly improved maximum entropy algorithm are compared. At the same time, two important indicators of image segmentation evaluation index regional consistency are used to evaluate the results. It shows that the experimental results of the algorithm have better intra-regional consistency and noise immunity.