Traditional threshold image segmentation method is a time consuming problem, we aim to find an effective optimal tool for proper threshold segmentation methods (e.g. Otsu and Kapur). In this work, we present a learning strategy based particle swarm optimization algorithm with an exchange method (LPSOWE). First, for enhancing the exploration ability and maintaining the convergence rate of the traditional particle swarm optimization algorithm (PSO), new jumping operators and learning items are proposed for a favorable update equation of PSO. Second, since particles are updated as a whole item in PSOs, a random cross operator and an exchange strategy are further investigated for the particles to have more chances for exploring the search space on each dimension. The Berkeley segmentation data set is used for comparisons with other algorithm and the results show that the proposed algorithm gets better results over the Evolutionary Computation (EC) based algorithms.
Bibliographical noteThe authors acknowledge support from the Macau Science and Technology Fund (FDCT 093/2014/A2, 008/2013/A1), the Research Committee of University of Macau (MYRG2015-00011-FST, MYRG2015-00012-FST), National Nature Science Foundation of China (No. 61571236, 61533010, 61203196), and Jiangsu Province Postdoctoral Science Foundation (No. 1402018A).
- Exchange method
- Learning item
- Particle swarm optimization
- Threshold image segmentation