基于严格等价函数的区间二型模糊熵及其图像阈值分割方法

Entropy of Interval Type-2 Fuzzy Sets and its Thresholding Method Based on Restricted Equivalence Functions

文中利用严格等价函数提出一种基于区间二型模糊熵的图像阈值分割方法.首先基于公理化定义,利用严格定价函数提出一种区间二型模糊熵的构建方法,由此可以得到多个不同的模糊熵计算表达式;然后通过理论分析给出了利用最小化模糊熵准则选取最优阈值的方法.实验结果表明,与现有的其他模糊阈值分割法和改进的2维Otsu法等相比,该方法的分割更加准确,运行时间更少,具有更广泛的适应性.

By using restricted equivalence functions, an image thresholding method based on entropy ot In- terval type-2 fuzzy sets is proposed. Firstly, on the basis of the axiom definition, a construction method of entropy measure for interval type-2 fuzzy sets is presented, so that some different formulas are derived to calculate this kind of entropy. Then, through theory justification the optimal threshold can be determined by minimum fuzzy entropy criterion. Finally, experiments demonstrate that, compared with other fuzzy thresh- olding methods and improved 2-D Otsu＇s methods, the method can achieve accurate segmentation results and has excellent adaptive capability.