模糊理论改进算法的CT图像弱边缘检测  

Weak edge detection of CT image based on improved algorithm of fuzzy theory

作　　者：黄朕[1] 高富强[1,2] 郑忠义 陈春江[1] 栗忍 

机构地区：[1]重庆大学自动化学院,重庆400030 [2]重庆大学光电技术及系统教育部重点实验室ICT研究中心,重庆400030 [3]铁牛科技,四川绵阳621000

出　　处：《强激光与粒子束》2014年第5期280-284,共5页High Power Laser and Particle Beams

基　　金：中央高校基本科研业务费专项资金项目(CDJZR12120006)

摘　　要：为改进传统工业CT图像弱边缘检测效果及速度不佳问题,研究了基于分步式模糊推理法与改进解模糊算法的CT图像弱边缘检测方法。选取了相关度、一致性测度、梯度作为模糊化特征,推理过程中相对于整体推理法,采用了Mandani推理法依据简化的推理规则表进行分步模糊推理,在解模糊过程中依据隶属度函数图像提出改进解模糊方法。通过实验验证得出分步推理法对CT图像弱边缘的检测效果更好。在保证解模糊精度的前提下,采用重心法改进的解模糊法,相对传统方法计算速度有了很大提高。In order to solve the weak edge detection of traditional industrial CT images shortcomings of poor detection effect and low speed, a detection method of step fuzzy inference algorithm and another method of improved defuzzification algo rithm were researched. Compared with overall reasoning method, the step fuzzy inference algorithm selected similarity, gradient and consistency as blur characteristics. And the reasoning process used Mandani reasoning to conduct step fuzzy reasoning, which was based on simplified inference rule tables. Improved defuzzification algorithm was proposed in the solution process. According to membership function figure, the two methods were verified by experiments. The results showed that the step fuzzy inference algorithm was better in the weak edge detection, while the improved defuzzification algorithm greatly increased the computing speed on the premise of accuracy.

关 键 词：模糊理论 CT图像 弱边缘检测 分步推理 改进解模糊 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]