一种基于概率配分和最大模糊熵的CT图像分割方法

为了从CT图像中提取到多个组织的解剖特征,克服运算速度快与运算结果不稳定的矛盾,提出了一种基于概率分布和模糊熵的CT图像分割方法。为了找到分割灰度图象的最佳阈值,根据模糊聚类和概率配分之间的关系,以及模糊熵有最大值的必要条件,从而得到各类的概率配分,因此在搜索阈值组合时,先搜索满足各类概率配分的阈值,然后从这些阈值中搜索使模糊熵最大的阈值。实验结果表明该方法能很好地完成CT图象的分割。此算法运算速度较快;与用遗传算法、模拟退火算法相比较,运算结果稳定,分割更准确。

CT Image Segmentation Based on Probability Partition and Maximum Fuzzy Entropy

In order to extract anatomical feature of several tissues from CT image and solve the contradiction between the improvement of the searching speed and instability of the results,a method for image segmentation using probability partition and maximum fuzzy entropy is proposed.In this method,in order to find the optimal threshoding,based on the relationship between the fuzzy clustering and probability partition and a necessary condition of having maximum fuzzy entropy,the probability partition of each part is derived.In the process of searching the thresholding set,we should firstly start with searching the thresholding set that satisfy probability partition and then optimal set can be found by looking for the maximum entropy from them.The experiment results show that our proposed method gives good performance for CT image segmentation.The search speed is quick and the results are steady than using genetic algorithm or simulated annealing algorithm and segmentation is more exact.