基于HALCON的汽车涂胶质量检测方法研究

针对汽车涂胶过程中漏涂、胶线过窄或过宽等问题,提出了一种基于Halcon的汽车涂胶质量检测方法。通过提取所采集的汽车胶条图像中感兴趣区域(ROI),设计了最大类间方差自动取阈值图像分割算法,提出了基于形态学的Canny算子边缘检测算法和基于XLD形状选择的最小二乘拟合算法,通过提取胶条的亚像素边缘,得到胶条的亚像素轮廓并计算出胶条的截面直径,判断胶条质量是否满足质量标准。最后采用HALCON软件对所设计的算法进行了验证测试,实验结果表明该方法具有较高的检测精度和检测效率,能够满足实际生产的需要。

Research on Quality Inspection Method of Automobile Gluing Based on HALCON

The work aims to process a design scheme for automotive rubber coating quality based on Halcon with respect to the problems of leakage coating,narrow or wide glue line in the process of automobile rubber coating.The maximum inter-class variance image segmentation algorithm is designed by extracting the region of interest(ROI)from the collected car strip image.The morphology based Canny operator edge detection algorithm and least squares based XLD shape selection are proposed.The algorithm extracts the sub-pixel edge of the strip to obtain the sub-pixel profile of the strip and calculates the cross-sectional diameter of the strip to determine whether the strip quality meets the quality standard.Finally,the designed algorithm is verified by HALCON software.The experimental results show that the method has high detection accuracy and detection efficiency,which can meet the needs of actual production.