中文摘要：

利用量子粒子群优化算法（QPSO）对二维Fisher准则图像分割评价函数进行了全局优化，提高了分割阈值的求解速度。并针对量子粒子群优化算法存在收敛性差、易早熟的问题，提出了量子粒子群优化算法和邻域搜索双重寻优的改进算法。实验结果表明，改进后的分割方法具有良好的分割效果和求解速度。寻找到的最佳阈值与二维Fisher准则函数算法完全相‘同，而阈值求解时间只有二维Fisher准则函数算法的1／3。

英文摘要：

The Quantum-behaved Particle Swarm Optimization （QPSO）algorithm is used to do the global optimization to the 2D Fisher criterion function of image segmentation, and the solving speed of segmentation threshold is improved. And according to the problems of poor astringency and premature occurrence in QPSO, a dual searching algorithm for best threshold is proposed, which consists of the steps of QPSO and searching neighborhood. The experimental results show that the improved image segment approach has good computation accuracy and speed. The best threshold found is perfectly matched with the one found by using 2D Fisher criterion function, but the computing time rates only one third.