文献类型：期刊文献

中文题名：一种改进的阈值分割算法在复合材料图像处理中的应用

英文题名：An Improved Threshold Segmentation Algorithm and Its Application in Image Processing of Composites

作者：李想[1];万永菁[1];周又玲[1]

机构：[1]华东理工大学信息科学与工程学院,上海200237

年份：2006

卷号：5

期号：4

起止页码：467

中文期刊名：江南大学学报（自然科学版）

外文期刊名：Joural of Jiangnan University (Natural Science Edition)　

收录：CSTPCD

语种：中文

中文关键词：阈值分割;模糊逻辑;纤维增强复合材料;最大熵算法

外文关键词：threshold segmentation; fuzzy logic;fiber-reinforced composites; maxim entropy thresholding

摘要：针对纤维增强复合材料微观结构图像的特点,提出了一种改进的基于模糊思想的阈值分割算法,该算法利用整体阈值、局部阈值和像点梯度信息之间的关系,构造了一个双输入单输出的模糊逻辑系统,合理计算出像点的最佳分割阈值.实验结果证明了算法的有效性.
Considering the characteristics of the microstructure image of fiber- reinforced composites, an improved threshold segmentation algorithm based on fuzzy theory is proposed in the paper. By using the relationship of the overall threshold of the image, part threshold and the gradient information of a pixel point, a fuzzy logical system with two inputs and one output is designed in the algorithm and the reasonable segmentation threshold of each pixel point is calculated. The validity of the algorithm is proved by the experiment results.