改进的二维Otsu图像分割方法及其快速实现

通过实验和理论验证2维直方图的副对角区域的概率和不一定很小而不能忽略，因而传统2维Otsu法中关于主对角区域的概率和近似为1的假设不够合理。针对该问题，该文提出了一种改进的2维Otsu法及其快速实现。新方法舍弃了不合理的假设，通过单独计算2维直方图主对角区域概率的方法，来准确估计主对角区域中目标和背景的概率，并重新计算2维Otsu。实验结果表明，改进的2维Otsu法能够获得明显优于传统2维Otsu法的分割效果，其快速算法的计算复杂度与传统2维Otsu法的快速算法相当。

Improved Two-Dimensional Otsu Image Segmentation Method and Fast Recursive Realization

Traditional 2D Otsu’s method supposes that the sum of probabilities of main- diagonal distinct in 2D histogram is approximately one. This paper’s experiments and theory prove that the sum of probabilities of counter-diagonal distinct in 2D histogram is not always very small and this could not be neglected. Therefore, the assumption mentioned above in 2D Otsu’s method is inadequately reasonable. In this paper, an improved 2D Otsu’s segmentation method and recursive algorithm are proposed. By separately calculates probabilities of objects area and background area in 2D histogram main-diagonal distinct, modified method is acquired. Experimental results show that proposed method can obtain better segmentation effect than the traditional 2D Otsu’s method. The computation complexity of improved 2D Otsu’s method corresponds to traditional 2D Otsu’s method.