基于小波及自适应Canny的磁环表面缺陷检测算法-计算机系统应用.PDFVIP

2016 年 第 26 卷 第 6 期 计 算 机 系 统 应 用 ① 基于小波及自适应Canny 的磁环表面缺陷检测算法 侯海洋, 李俊峰 (浙江理工大学 自动化系, 杭州 3 10018) 摘 要: 对常规分割算法难以将磁环缺陷从纹理复杂的磁环表面提取出来, 本文提出了一种基于小波变换及 边缘检测的缺陷提取算法. 基于小波变换对磁环纹理的弱化作用, 对小波分解低频部分采用自适应 Canny 边缘检 测算法分割出含缺陷的边缘; 基于阈值分割的轮廓查找算法, 提取出磁环内外轮廓并作一定的处理; 对含缺陷边 缘和处理后内外轮廓做形态学处理和逻辑运算提取出磁环所有缺陷; 对缺陷排序并提取出磁环主缺陷轮廓, 判 断轮廓闭合情况并填充轮廓得到主缺陷区域. 实验表明本文算法正检率达 94.7%. 关键词: 磁环表面缺陷; 小波变换; 自适应Canny 边缘检测; 轮廓查找; 形态学处理 Magnetic Ring Surface Defect Detection Algorithm Based on Wavelet and Adaptive Canny Operator HOU Hai-Yang, LI Jun-Feng (Department of Automation, Zhejiang Sci-Tech University, Hangzhou 310018, China) Abstract: Aiming at the problem that the normal segmentation algorithms is difficult to detect the defects from the surface of magnetic ring with complex texture, this paper proposes a novel edge detection algorithm based on wavelet. Based on the weakness to magnetic ring texture using wavelet, Canny edge detection algorithm is adapted to segment the defect edge for the low frequency part after wavelet decomposition and reconstruction. By the find contours algorithm based on threshold segmentation, the magnetic inner-outer contour is extracted and processed. Through morphological processing and logical operation of the defective edge contours, all defects of magnetic ring are abstracted. After sorting the defects and abstracting the main contours of defects, we can judge the contour closure and fill the contour to get the main defect area. Experimental results show that the algorithm has a positive detection rate of 94.7%. Key words: magnetic ring surface defect; wavelet; adaptive Canny edge detection; find contours; morp