基于BBO算法的二维交叉熵多阈值图像分割*

针对复杂图像的分割问题,提出一种基于生物地理学优化算法(BBO,Biogeography-Based Optimization)的二维交叉熵多阈值图像分割方法。首先,根据二维直方图斜分法得出交叉熵阈值选取公式,并将此推广到多阈值分割,以求得多个极值提高分割效果,由于二维交叉熵法在多阈值分割时计时长、复杂性高等问题,然后引入BBO算法的思想,实现对多个阈值快速精确地寻优,最后,对标准图像进行分割以验证该算法。结果表明此算法比二维交叉熵穷举法计算效率高。

Two-dimensional cross entropy multi-threshold image segmentation based on BBO algorithm

In this paper, a two-dimensional cross entropy multi-threshold image segmentation method based on Biogeography-Based Optimization (BBO) is proposed to solve the problem of segmentation of complex images. First of all, according to the two-dimensional histogram oblique segmentation method, cross entropy threshold selection formula was obtained and extended to the multi threshold segmentation. multi extremum was got in order to improve the segmentation performance .Because of the high complexity in the process of multi threshold segmentation, the BBO algorithm was introduced to realize the fast and accurate optimization of multiple thresholds. Finally, the standard image was segmented to verify the algorithm. The results show that the algorithm is more efficient than the two-dimensional cross entropy method of exhaustion.