摘要
为提高钢球表面缺陷检测的效率和准确性,设计一种基于机器视觉的钢球表面缺陷分拣系统。对钢球表面图像进行图像分割、平滑去噪和二值化预处理,获取钢球表面图像的准确信息,并采用改进的中值滤波算法去除噪声;利用小波变换和多尺度形态学融合算法进行钢球表面缺陷的边缘检测;通过该融合算法和其他算法的检测结果对比和客观数据评价,验证了本文所提算法能够有效保留图像真实细节,并满足钢球分拣系统的需求。
In order to improve the efficiency and accuracy of steel ball surface defect detection,a steel ball surface defect sorting system based on machine vision is designed.The image of steel ball surface is preprocessed,which includes image segmentation,smoothing de-drying and binarization.In the aspect of noise removal,an improved median filter algorithm is used to obtain accurate information of steel ball surface image.The edge detection of steel ball surface defects is carried out by combining wavelet transform and multi-scale morphology.The edge detection of steel ball surface defects is carried out by this method.The proposed fusion algorithm is compared with other algorithms and the objective data evaluation proves that the proposed algorithm can effectively retain the real details of the image and meet the needs of the steel ball sorting system.
作者
范峥
刘刚
Fan Zheng;Liu Gang
出处
《工具技术》
2019年第9期102-106,共5页
Tool Engineering
基金
河南省科技计划项目(182102210261,192102210063)
关键词
多尺度形态学
小波变换
钢球表面缺陷检测
边缘检测
图像处理
multi-scale morphology
wavelet transform
steel ball surface defect detection
edge detection
image processing
作者简介
第一作者:范峥,教授,河南工学院电气工程与自动化学院,453000河南省新乡市.
