Abstract:

In view of the high cost and low effectiveness of current detection methods for some elliptic hole group workpieces,an elliptic hole group detection method based on maximal inscribed circle was proposed. Firstly, the image was preprocessed by denoising, binaryzation and edge detection. According to the geometric properties of ellipse, the ellipse's maximal inscribed circle was calculated by using the ellipse center estimation method and the distance selection method. Then, the center coordinates of the ellipse, the length of long and short axes and the inclination angle were determined. The experimental results show that the proposed method can quickly and accurately detect the elliptic hole group, and can quickly intercept effective ellipse arc based on the estimation of the center of the ellipse, then the invalid samples are reduced; compared with the Hough ellipse detection algorithm based on center estimation and the ellipse detection algorithm based on the improved least square method, it has the advantages of high precision, short time consumption, and can be effectively applied to automatic detection of elliptical hole group workpieces.

Key words: machine vision, edge detection, center estimation, maximum inscribed circle, ellipse detection

摘要：

针对当前一些椭圆孔组工件检测成本高、时效低等问题,提出了一种基于最大内切圆的椭圆孔组检测方法。首先对椭圆孔组图像进行去噪、二值化和边缘检测等预处理;再根据椭圆的几何性质,结合椭圆中心估计方法和最值距离选取方法,求出椭圆最大内切圆,从而确定椭圆的中心坐标、长短轴长和倾斜角。实验数据表明,该方法能对椭圆孔组进行快速精确检测,在估计出椭圆中心的基础上能快速截取有效椭圆弧,大幅减少无效采样;与基于中心估计Hough椭圆检测算法和基于最小二乘改进椭圆检测算法相比,具有耗时短、精度高等优点,可有效应用于椭圆孔组工件的自动化检测。

关键词: 机器视觉, 边缘检测, 中心估计, 最大内切圆, 椭圆检测