论文部分内容阅读
为了提高烟丝宽度的检测效率,研究了烟丝切口快速识别与宽度测量方法。采用张正友标定法对烟丝图像进行了畸变校正,使用了基于RGB(Red-Green-Blue)颜色空间的RB分量差值阈值分割法,实现了烟丝与背景图像的精确分割,提出了计算效率较高的烟丝切口位置识别算法,通过计算烟丝两侧切口位置的距离,实现了无规则摆放烟丝的宽度测量,并以简单随机抽样为理论依据,计算了该方法的最佳样本容量为30。实验结果表明,该方法的重复性限约为0.07 mm,测量误差约0.007 mm,耗时约是ISO方法的1/8。
In order to improve the detection efficiency of tobacco width, the rapid identification and width measurement of cut tobacco were studied. Zhang Zhengyou calibration method was used to correct the distortion of the cut tobacco image. The RB component difference threshold segmentation method based on RGB (Red-Green-Blue) color space was used to achieve the accurate segmentation of the cut tobacco and the background image. A high computational efficiency The calculation of the distance between the cuttings on both sides of the cut tobacco achieves the measurement of irregular cut tobacco width. Based on the simple random sampling theory, the optimal sample size of the cut tobacco is calculated as 30. The experimental results show that this method has a repeatability limit of 0.07 mm, a measurement error of about 0.007 mm and a time-consuming about one-eighth of the ISO method.