薄片零件尺寸机器视觉检测系统研究与开发

Research and Development of Dimensional Inspection System for Thin Sheet Part Based on Machine Vision

对薄片零件尺寸机器视觉检测系统的关键技术进行研究,开发一套完整的机器视觉检测系统。提出基于CAD信息的线扫描步长自适应优化方法用于被检测零件的图像采集;提出基于三次样条插值的矩形透镜法亚像素边缘检测方法用于边缘检测;提出基于曲率与HOUGH变换的平面轮廓图元识别方法用于图像识别。实验结果表明:检测系统的检测精度能达到1μm,检测时间能满足实时在线检测的要求,该检测系统是可行的。

Key technologies of dimensional inspection system for thin sheet part based on machine vision were investigated,and an entire machine vision inspection system was developed.A CAD information-based line scanning step self-adaptive optimization method used for image grabbing of inspected part was proposed.A rectangle lens subpixel edge detection method based on cubic spline interpolation used for edge detection was advanced.A planar contour primitive recognition method based on curvature and HOUGH transform used for image recognition was raised.The experimental results show the inspection accuracy of the inspection system can reach to 1μm,and the inspection time can satisfy the requirements of on-line real-time inspection,so the inspection system is feasible.