论文部分内容阅读
微小孔系的精密测量用传统的手段是难以实现的。以机器视觉为基础,结合计算机图像处理技术可完成这类测量任务。介绍了基于机器视觉的孔系精密测量系统的硬件组成和图像处理算法。以所提出的识别弦端点来确定图像圆心坐标的算法对500根弦的中点坐标进行滤波处理,可使识别误差达到亚像素级。圆心坐标在X和Y方向的标准差均小于4μm,孔系间角度测量标准差小于3″。
The precise measurement of micropore lines is difficult to achieve with traditional methods. Based on machine vision, combined with computer image processing technology to complete this type of measurement tasks. The hardware components and image processing algorithms of hole-based precision measurement system based on machine vision are introduced. With the proposed algorithm to identify the coordinates of the center of the circle by the end point of the string, the mid-point coordinates of 500 strings are filtered to make the recognition error reach the sub-pixel level. The standard deviation of the center coordinates in the X and Y directions is less than 4μm, and the standard deviation of the angle between the holes is less than 3 ".