提出了一种基于机器视觉的非接触测量方案，力求把非接触测量手段与零件尺寸测量问题更有效地结合起来。采用超分辨率重构技术消除噪声以及由有限检测尺寸和光学元件产生的模糊，从图像中获得更多的细节和信息。利用最小二乘回归亚像素边缘检测技术进行边缘定位及角点提取。基于机器视觉CCD摄像机采用线性回归法进行摄像机的标定。最后，实验分析和比较了基于机器视觉的零件尺寸测量的应用效果。

A project of untouched measurement based on machine vision is proposed to combine the newest untouched measurement technique with the problem of size measurement of parts. Firstly, the noise and blur caused by limited detection size and optical element using super resolution reconstruction technique are eliminated with the super resolution reconstruction technique to get more details and information from captured images. Secondly, the least-squares regression sub-pixel edge detection technique is used to orientate edge and extract corner points. Thirdly, camera parameters are calibrated by using least-squares regression method based on machine vision. At last, the size measurement result of parts based on machine vision by experiment is analyzed.