基于模糊推理的边缘检测新算法

摘要

研究了原有的基于模糊推理的边缘检测算法.在分析原有算法存在问题的基础上,提出了一种新的模糊化规则,利用方向灰度对比度去确定边缘隶属度值,增加了去除伪边缘的规则,使得边缘细化.对原有算法和新算法进行了品质因素和平均运行时间的算法性能的对比、分析.%This paper analyzes the original about edge detection algorithm based on fuzzy inference. Based on analysis of the original algorithm,new fuzzy rules are proposed that use the contrast of gray-scale's direction to determine the value of edge's membership and increase the rules to remove false edge and make edge refined. It compares the quality factors and the average running time between the original algorithm and new algorithm.