.png){kind=icon}
返回
A hybrid cooperative-comprehensive learning based PSO algorithm for image segmentation using multilevel thresholding
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2007.01.002.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
A novel optimal multilevel thresholding algorithm for histogram-based image segmentation is presented in this paper. The proposed algorithm presents an improved variant of PSO, a relatively recently introduced stochastic optimization strategy. This hybrid approach employs both cooperative learning and comprehensive learning along with some additional modifications. Cooperative learning is employed to overcome the curse of dimensionality by decomposing a high-dimensional swarm into several one-dimensional swarms. The comprehensive learning is then employed to discourage premature convergence in each one-dimensional swarm. The capability of this hybrid PSO (called HCOCLPSO) is further enhanced by cloning of fitter particles, at the expense of worst particles, determined on the basis of their fitness values. The performance of HCOCLPSO algorithm is evaluated vis-A-vis an improved GA-based algorithm [Yin, P.-Y., (1999). A fast scheme for optimal thresholding using genetic algorithms. Signal Processing 72, 85-95], Gaussian-smoothing method [Lim, Y. K., & Lee, S. U., (1990). On the color image segmentation algorithm based on the thresholding and the fuzzy c-means techniques. Pattern recognition. 23, 935-952; Tsai, D. M. (1995). A fast thresholding selection procedure for multimodal and unimodal histograms. Pattern Recognition Letters 16, 653-666] and symmetry/duality method [Yin, P. Y., & Chen, L. H., (1993). New method for multilevel thresholding using the symmetry and duality of the histogram. Journal of Electronics and Imaging 2, 337-344] for several benchmark images and HCOCLPSO outperforms each of these algorithms for each such image. (C) 2007 Elsevier Ltd. All rights reserved.
Keyword:
PSO
cooperative learning
comprehensive learning
HCOCLPSO
image segmentation
multilevel thresholding
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
