基于IGA与GMM的图像多阈值分割方法

Multilevel thresholding method based on immune genetic algorithm and Gaussian mixture model for image segmentation

为了实现图像的有效分割,提出了一种自适应多阈值图像分割方法,能够自动获得最佳分割阈值数目和阈值。该方法对灰度直方图进行合适尺度的连续小波变换,将小波变换曲线中幅值为负的波谷点构成阈值候选集;再应用免疫遗传算法从阈值候选集中选取准阈值,准阈值的个数对应为最佳分割类数;根据准阈值构建灰度直方图的高斯混合模型,由最小误差准则求得分割阈值。仿真实验表明,该方法能够实现图像的自动多阈值分割,能够得到很好的分割结果且分割效率高,在多目标图像分割中能够得到很好的应用。

This paper proposed an adaptive multilevel thresholding algorithm based on immune genetic algorithm and Gaussian mixture model for image segmentation. The method allowed the determination of the appropriate number of thresholds as well as the adequate threshold values. The threshold candidate set with limited valley points could be attained by means of transforming the histogram with the right scale continuous wavelet. Then, determined the number of thresholds and the quasi-threshold values by using the immune genetic algorithm. The parameters of Gaussian mixture model could be received by the way of fitting the histogram with the quasi-threshold values： Last, the segmentation thresholds could be attained by using of the minimum error criterion. Simulation results show that this algorithm is very well in improving the speed, and good segmentation results can be received.