基于粒子群优化算法的自适应图像分割方法

Adaptive segmentation method based on particle swarm optimization algorithms

提出了一种基于粒子群优化算法的图像分割新方法。粒子群优化(PSO)算法是一类随机全局优化技术,它通过粒子间的相互作用发现复杂搜索空间中的最优区域缩短了寻找阈值的时间。将PSO用于基于改进的最佳加权熵阈值法的图像分割中,试验结果表明,该方法不仅能够避免陷入局部极值,而且其速度得到了明显的改善,是一种有效的图像分割新方法。

A new method for image segmentation based on particle swarm optimization（PSO） algorithms is presented. Particle swarm optimization algorithms are a stochastic global optimization technique. The algorithms find optimal regions of complex search spaces through the interaction of individuals in a population of particles. The method based on improved optimal weighted entropic threshold is implemented using PSO. Optimum parameters suitable for this algorithm based on improved PSO are given. The experimental results indicate that the new approach can shorten the computational time compared whh other traditional ways, and is effective for image segmentation.