基于二维Renyi熵与自适应人工鱼群算法的红外图像分割

Infrared Image Segmentation Based on AAFSA and 2D-Renyi Entropy Threshold Selection

针对基于分解的二维renyi熵阈值分割算法中参数α的取值问题,根据均匀性测度评价指标,利用自适应人工鱼群搜索方法,提出一种α参数自适应选取方法。实验结果表明,本文所提出算法,针对不同红外图像均可以获得理想的图像分割效果,具有良好的通用性。同时还可以将算法计算复杂度由O(L6)降为O(L2)。

To select optimal parameter a in decomposed 2D-renyi entropy image threshold segmentation method,a new adaptive method according to the uniformity measure which is an image segmentation evaluation criteria is proposed based on adaptive artificial fish-swarm algorithm.Experiment results show that the method can get desired segmentation result for each image.The algorithm is of universality and can also reduce the computational complexity from O（L6）to O（L2）.