基于改进Sobel算子的表面裂纹边缘检测算法  

A surface crack edge detection algorithm based on improved Sobel operator

作　　者：张建军 罗静[1] 

机构地区：[1]合肥工业大学计算机与信息学院,安徽合肥230009

出　　处：《合肥工业大学学报（自然科学版）》2011年第6期845-847,960,共4页Journal of Hefei University of Technology：Natural Science

基　　金：国家高技术研究发展计划(863计划)资助项目(2004AA424521)

摘　　要：文章针对经典Sobel边缘检测算子存在图像边缘定位精度不高和对噪声敏感等缺点,通过分析引水压力钢管表面裂纹图像的特点,提出了一种改进算法。首先增加6个方向模板,提高定位精度;其次,对于使用8个方向模板检测的图像运用迭代阈值分割算法进行二值化处理,去除伪边缘;最后利用形态学膨胀算法连接裂纹。经实验证明,该算法能够有效地提取裂纹边缘信息和连接裂纹。To solve the drawbacks of classical Sobel edge detection operator such as low image edge positioning accuracy and being sensitive to noise,this paper proposes an improved algorithm by analyzing the image characteristics of surface cracks on steel pressure pipe.Six orientation templates are firstly added to improve the edge positioning accuracy.Then a binary image is produced from the outcoming image measured by eight orientation templates through adopting the iterative segmentation algorithm so as to eliminate the false edges.Finally the fracturing cracks are connected by using morphological expansion algorithm.The experiments verify that the algorithm can extract the information of crack edges and connect fracturing cracks effectively.

关 键 词：边缘检测 SOBEL算子 迭代阈值 形态学膨胀 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]