一种基于自适应最小模糊熵的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,解决运算速度的提高与运算结果不稳定的矛盾,我们提出了一种基于自适应最小模糊熵的图像分割算法.为了找到分割灰度图像的最佳阈值.首先利用迭代公式以及图像的直方图来计算出每个模糊子集的隶属函数中指数参数的值以及阈值的搜索范围,然后在已确定的搜索范围内用穷举法搜索出能使模糊熵最小的最佳阈值.实验表明该方法能较好的完成CT图像的分割.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,重复性更好,得到的图像细节成分要更多些.

CT Image Segmentation Based on Automatic Adaptive Minimal Fuzzy Entropy Measure

In order to extract the anatomical feature of several tissues from CT image and solve the contradiction between the improvement of searching speed and the instability of results,we propose a method for image segmentation using auto adaptive minimal fuzzy entropy measure. Firstly, to find the optimal threshoding for segmenting image, the values of the exponent parameters of membership function of fuzzy subsets and the range of the searching thresholding values can be determined by using the iterative approach and the image histogram, and then the thresholding of minimizing the fuzzy entropy is implemented by searching all possible combinations of every thresholding in determinate searching range. The experiment results show that our proposed method facilitates good performance for CT image segmentation. The searching speed is quick, the segmented images show more details, and the results of many runs are steadier than those obtained by using genetic algorithm or simulated annealing algorithm.