基于机器视觉的圆锥滚子外观缺陷检测系统研究

Research on Inspection System of Tapered Roller's Appearance Defect Based on Machine Vision

摘要:

回顾了近年来国内外工业生产中圆锥滚子外观缺陷分割领域的研究进展,为了实现更加简单高效的滚子外观缺陷检测,设计了一套合适的光学成像系统用于图像采集,提出了最大类间方差法和局部阈值算法的缺陷分割,对分割后图像进行特征提取并进行SVM分类;实验结果表明,该算法有较高的准确率和较好的适应性,优于传统的滚子外观缺陷分割算法,可以满足工业生产中的实际需求。

Abstract:

Reviews in recent years appearance defects of domestic and foreign industrial production in the tapered roller segmentation research progress, in order to achieve a more simple and efficient roller appearance defect detection proposed a set of complete image processing algorithms. A suitable optical imaging system is designed for image acquisition, the defect segmentation of the maximum between class variance method and local threshold algorithm is proposed, and then the feature extraction and SVM classification. The experimental results show that the algorithm has higher accuracy and better adaptability than the traditional method, which can meet the requirements of industrial production.