基于图像识别的齿轮尺寸测量研究

为解决传统工业测量中,齿轮参数尺寸测量方法过于繁琐的问题,利用数字图像处理技术对其进行检测,提出了一种基于圆投影分割的齿轮参数尺寸检测方法。该方法首先通过图像预处理得到细化的齿轮轮廓,使用改进随机采样算法找到齿轮中心;然后利用轮廓点和图像中心点连线与所建立的图像坐标系正向X轴所成角度和两点距离的映射关系,建立新的极坐标系,并对齿轮进行圆分割,记录新坐标系中峰值点个数和峰值点纵坐标,这2个参数分别对应齿轮齿数和齿顶圆半径;最后利用齿顶圆半径与齿数、模数之间的关系式,求出模数,从而求出齿轮其他尺寸。实验结果表明,用该方法检测齿轮参数尺寸,检测速度快、精确度高,具有较高的实用价值。

Parameter detection of spur gear based on circular projection segmentation

In order to solve probrem that in traditional industrial measurement,the size of the gear parameter measurement method is too cumbersome problem.By using digital image processing techniques to detect,put forward a kind of gear parameters based on circular projection segmentation size detection method,the method of gear contour extraction in the first place,and refine the contour edge,and then find gear center through improved random sampling fitting method,The line between the contour point and the center of the image,the included Angle formed by this line and the positive X-axis of the coordinate system and the mapping relationship between the contour point and the center,the new coordinate system was established.The experimental results show that this method has the advantages of high speed,high accuracy and high practical value.