基于机器视觉和改进形态学边缘检测算法的钢球缺陷检测技术研究
2019-08-30
作者：范峥，刘刚
单位：河南工学院
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。
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
中图分类号：TG87；TH74；TP391.4文献标志码：ADOI：10.3969/j.issn.1000-7008.2019.09.026
Research on Steel Ball Defect Detection Technology Based on Machine Vision
and Modified Morphological Edge Detection Algorithms
Fan Zheng，Liu Gang
Abstract: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 dedrying 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 multiscale 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.
Keywords:multiscale morphology；wavelet transform；steel ball surface defect detection；edge detection；image processing