纹理分类中遗传算法参数的选择

The Parameters Selection of Genetic Algorithms in Texture Classification

本文详细分析遗传算法（简称ＧＡ）中群体的大小、交叉率和变异率选择对纹理分类的影响，并对繁衍过程中如何拷贝（即复制）产生新群体的问题进行了研究。研究表明，应当用适应度最好的个体取代淘汰的个体，将使解的收敛速度大大提高。

This paper analyzes the influence of population size, crossover probability and mutation probability in genetic algorithm on texture classification, and discusses how to copy new population in reproduction process. The study shows that the best individual should be used to take place of the obsoleted individuals, so that the convergent speed of solutions can be improved greatly.