基于多模糊阀值分割技术图像边沿提取方法研究  

Image Edge Extraction Method Based on Multi-fuzzy Threshold Segmentation Technology

作　　者：黄秀常[1] HUANG Xiu-chang(Institute of Mechanical and Electrical Information,Yiwu Industrial and Commercial College,Yiwu Zhejiang 322000,China)

机构地区：[1]义乌工商职业技术学院机电信息学院,浙江义乌322000

出　　处：《菏泽学院学报》2018年第5期22-26,共5页Journal of Heze University

摘　　要：传统Sobel算子、Canny算子、图像分割技术中需要多个固定阀值作为约束条件,阀值缺少关联性,分割精度差.提出了一种基于多模糊阀值分割技术的图像边沿提取方法,通过对图像进行尺寸与灰度预处理得到边沿区域明显灰度图像,然后通过模糊阀值算法提取图像主要轮廓,以确保提取边沿完整性,确定最佳阀值计算完成图像边沿的提取.实验结果表明,与传统自适应阀值分割算法相比,该算法在滤除图像噪声、保留细节边缘和保持图像边缘连通性方面以及清晰度都获得了不错效果,提高了边沿提取效率,节省时间,且增强了图像处理普适性,更具有实用性.Traditional Sobel operator, Canny operator and image segmentation technology need many fixed thresholds as constraints. The thresholds lack relevance and the segmentation accuracy is poor. In this paper, an edge extraction method based on multi-fuzzy threshold segmentation technology is proposed. The edge region gray image is obtained by preprocessing the image size and gray level. Then the main contour of the image is extracted by fuzzy threshold algorithm to ensure the integrity of the edge extraction, determine the optimal threshold calculation and complete the image edge extraction. The experimental results show that compared with the traditional adaptive threshold segmentation algorithm, this algorithm achieves good results in filtering image noise, retaining detail edges, maintaining image edge connectivity and clarity, improves the efficiency of edge extraction, saves time, and enhances the universality of image processing, which is more practical.

关 键 词：模糊阈值 图像分割 边沿 资格函数 模糊属性 

分 类 号：TP931[自动化与计算机技术]