【摘要】 易开盖刻痕深度是决定罐头包装质量的关键参数。为了满足在工业现场自动测量刻痕深度的准确度和稳定性要求,提出了一种基于光切法的机器视觉系统,具有三维精密定位功能和图像测量功能。针对易开盖刻痕光切图像特点,实验分析了在x-y平面上不同测量位置与光带斜率之间的几何关系,提出一种平面定位算法来自动检测和矫正光带投射位置;采用6种调焦函数对光切图像进行处理,以单峰型和无偏性为评价标准,提出一种以灰度变化率之和函数为粗调焦函数,Laplacian函数为细调焦函数的调焦算法,来调整被测刻痕在z方向上的正确成像位置,实验结果表明该算法具有良好的单峰性、无偏性和灵敏度。更多还原

【Abstract】 The nick depth of easy open end is a key parameter in ensuring high packaging quality. In order to realize automatic detection of easy open end in industrial production sites and improve the measurement accuracy and stability, a machine vision system based on light-section method is developed, which has a three dimensional positioning function and an image measuring function.In view of the light- sectioning image properities, the geometrical relationship between the measuring position and the notch slope in the x-y plane is analyzed through experiments to offer a two dimensional location strategy for automatically detecting and adjusting the light projection position. Through analyzing six focusing functions for the light-sectioning images,unimodal and unbiased as evaluation standard an automatic focusing algorithm based on the sum of gray rate of change function as rough focusing function and Laplacian function as fine focusing function is proposed to adjust the notch location. Experimental results show that the proposed algorithm has the strong single peak feature, good stability and high sensitivity.更多还原