利用Hough渐开线变换的齿轮图像中心检测

Gear Image Center Detection Using Hough Involute Transform

针对目前基于机器视觉的齿轮参数测量和检测中,获取齿轮中心坐标这一关键步骤缺乏通用性的问题,提出了一种利用Hough渐开线变换的方法。首先,在图像坐标中建立齿轮渐开线齿廓的数学模型。接着,对齿轮的灰度图像进行卷积、边缘检测获得齿轮边缘图像和像素梯度角。最后,对边缘像素做Hough渐开线变换,得到最终的齿轮中心坐标。实验和仿真结果表明,按该方法求得的结果与真实坐标的标准差在1 pixel以内,对齿轮内孔形状无要求,可以作为一种有效的齿轮图像中心检测方法。

In response to the key step of obtaining the gear center coordinates in current gear parameter measurement and detection based on machine vision,which lacks versatility,a method based on Hough involute transform was proposed.First,a mathematical model of gear involute tooth profile was established in image coordinates.Then performing convolution and edge detection to obtain the gear edge image and the pixel gradient angle.Finally,the gear center coordinate was found by performing Hough involute transform on the edge pixel.Simulation and experiment results show that the standard deviation of the real coordinates and the method's is within 1 pixel,and there is no requirement for the shape of the gear inner hole.It can be used as an effective method for gear center detection.