基于Opencv2的零件轮廓图像自动检测法研究

Research on automatic detection method of part contour image based on Opencv2

主要针对轴承类零件内外直径等圆形零件的拍照图片进行边缘检测与拟合,通过设定图片上正方形对照因子的实验的方法完成尺寸检测,利用Opencv2库中的Canny算子对零件的外直径尺寸进行标定,通过计算像素点的梯度值对内外轮廓进行拟合并测量。该技术可以在零件加工过程中实时检测零件加工切削尺寸是否合理,监测轮廓加工误差,提高工件的加工精度,并为改进加工方法提供数据支持。

In this paper,edge detection and fitting are carried out for the photos of circular parts such as the inner and outer diameters of bearing parts.The size detection is completed by setting the square contrast factor on the photos.The Canny operator in Opencv2 library is used to calibrate the outer diameter of the parts.The inner and outer contours are fitted and measured by calculating the gradient value of the pixels,this technology can real-time detect whether the cutting size is reasonable,monitor the contour machining error,improve the machining accuracy of the workpiece,and provide data support for improving the machining method.