一维对象复杂度的灰度图像分割算法

Grayscale image segmentation algorithm based on onedimensional object complexity

从图像复杂度的角度,提出一种一维对象复杂度的灰度图像分割算法。用阈值将灰度图像分为背景与目标2类,统计其对应直方图与总像素个数,并计算对象复杂度;依据图像复杂度分割准则算法公式,遍历每一灰度级对应的图像复杂度值,选取图像复杂度值最小对应的灰度值为最佳分割阈值。仿真实验结果表明,与经典Otsu算法、信息最大熵算法和最小交叉熵算法相比,本文算法速度快,稳定性和效率最好,是一种通用有效的图像分割算法。

Inspired by the classical segmentation algorithm,this paper proposes a grayscale image segmentation algorithm based on the image complexity.Firstly,the grayscale image is divided into background and target categories by the threshold,the corresponding histogram and total number of pixels are calculated,as well as the complexity of objects.Secondly,according to the image complexity segmentation criterion,the image complexity of each gray level is calculated.Finally,the optimal segmentation threshold is obtained by the minimum value of the object complexity.Compared with the other three classical algorithms,the experimental results show that the proposed image segmentation algorithm is fast,stable and efficient.