基于链式竞争遗传算法的KSW熵的图像分割

针对最佳熵阈值图像分割算法过程中计算复杂度高的问题,提出了一种基于链式竞争遗传算法的最佳熵阈值确定法(KSW熵法)的图像分割算法.通过将3个邻域的链式竞争引入到常规遗传算法框架下,实现特征选择过程;将改进的遗传算法应用到最佳阈值图像分割算法中,完成对阈值的寻优过程.仿真实验结果与分析表明:算法在分割速度和效果上均优于传统的最佳阈值图像分割算法和单纯的遗传优化最佳阈值图像分割算法.

Image segmentation of KSW entropic based on chain competitive genetic algorithm

Aiming at the problem of high computational complexity in the process of the optimal entropic threshold image segmentation algorithm,propose an image segmentation algorithm based on link-like competition genetic algorithm for optimum entropy thresholding method,i. e. KSW entropy(L-GA-KSW). In the process of algorithm realization,feature selection process is realized by introducing the chain competition of 3 neighboring chains into the framework of conventional genetic algorithm;then,the improved genetic algorithm is applied to the optimal threshold image segmentation algorithm to achieve threshold optimizing. Simulation results and analysis show that the algorithm is superior to the traditional image segmentation algorithm and the simple genetic optimization threshold image segmentation algorithm in segmentation speed and effect.