基于改进Canny算法的工件边缘检测方法

发布时间：2018-05-26 21:00

本文选题：工件边缘检测 + 改进Canny算法　；参考：《广西大学学报(自然科学版)》2017年06期

【摘要】：为了使区域模板匹配定位能够更准确地进行,需要机器视觉精准地检测出工件边缘信息,同时消除噪声、伪边缘等无关信息的干扰。针对采用Canny算法进行边缘检测时图像平滑处理过度、阈值需要预先确定、对无关信息消除能力较弱等缺点,提出一种基于改进Canny算法的工件边缘检测方法。采用双边滤波方法处理图像,以有效去除噪声并保留边缘信息;增加45°与135°方向的梯度模板计算梯度幅值,使更多的边缘信息能够检测出来;运用最大类间方差法来确定Canny算法的高阈值,使边缘检测算法具有较强的自适应能力。实验结果表明,改进的算法能够准确地检测到真实边缘,具备较强的自适应性,特别是对存在划痕的工件进行边缘检测时,此方法能够消除划痕干扰,其检测效果优于传统Canny算法。
[Abstract]:In order to make the matching localization of the region template more accurate, it is necessary to detect the edge information of the workpiece accurately by machine vision, and to eliminate the interference of irrelevant information such as noise, pseudo-edge and so on. In view of the shortcomings of image smoothing processing when using Canny algorithm for edge detection, the threshold needs to be determined in advance, and the ability to eliminate irrelevant information is relatively weak, a workpiece edge detection method based on improved Canny algorithm is proposed. In order to effectively remove noise and retain edge information, the two-sided filtering method is used to process the image, and to increase the gradient template in the direction of 45 掳and 135 掳to calculate the gradient amplitude, so that more edge information can be detected. The maximum inter-class variance method is used to determine the high threshold of the Canny algorithm, which makes the edge detection algorithm have a strong adaptive ability. The experimental results show that the improved algorithm can detect the real edge accurately and has strong adaptability. Especially for the work piece with scratch, the method can eliminate the scratch interference. Its detection effect is better than the traditional Canny algorithm.
【作者单位】：长春工业大学电气与电子工程学院;
【基金】：吉林省中青年科技创新领军人才及团队项目(201505190009JH) 吉林省教育厅“十三五”科学技术研究项目(2016338)
【分类号】：TP391.41

【相似文献】