面向Otsu阈值搜索的PSO惯性因子改进方法研究

针对快速寻找Otsu方法的最优阈值，提出了一种粒子群优化(PSO)算法中惯性因子的改进方法。 该方法使PSO的惯性因子与群最优适应值和个体最优适应值相关，惯性因子的大小由个体最优适应值与群最优适应值的距离决定，随着个体最优适应值与群最优值的距离减小，惯性因子也减小，反之则增加。通过与现有方法比较，结果表明：该方法计算量小，收敛速度快.

Study on Modifying Inertia Weight in PSO for Finding the Threshold of Otsu Rule

In order to find the threshold of Otsu rule rapidly, a modifying strategy to the inertia weight in particle swarm optimization(PSO)is introduced. This makes the inertia weight being updated by the distance between the best position of the individual particle and the globally best position. With the reduction of the distance between the globally best position and the individual best position, the inertia weight of the individual particle would be reduced, vice versa. The comparison results with other methods indicate that this algorithm has less computational work and a fast convergence.