一种基于机器视觉的螺纹缺陷检测方法  

Method for Detecting Thread Defects Based on Machine Vision

作　　者：施保华[1] 魏雅慧 

机构地区：[1]三峡大学电气与新能源学院,湖北宜昌443002

出　　处：《三峡大学学报（自然科学版）》2015年第2期64-66,共3页Journal of China Three Gorges University：Natural Sciences

基　　金：国家自然科学基金(51407104)

摘　　要：针对目前螺纹检测精度较低,在线检测实现较难的问题,提出了一种基于机器视觉的螺纹缺陷检测方法.通过工业CMOS相机在线采集螺纹零件图像,经图像预处理、二值化后,进行螺纹的边缘提取及缺陷检测等.该算法由Matlab编程实现.实验结果表明,该螺纹缺陷检测方法能有效识别无螺纹、少螺纹、螺距不规则等外观缺陷,且一个螺纹的检测时间在300ms以内,满足检测要求.A method for detecting thread defect based on machine vision is aiming at the problem of low precision and realizability.Thread images are taken by CMOS camera;and extraction of thread edge and detection of thread defect can be done after preprocessing and binarization.The method is realized by Matlab programming.Experimental results show that the method can identify non-thread,less-thread,uneven pitch and other defects.The detection time of a thread is less than 300 ms that meets the detection requirements.

关 键 词：机器视觉 螺纹 边缘提取 缺陷检测 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置]