基于改进随机Hough变换的椭圆形农产品大小分级

针对椭圆形农产品的分级问题,采用最近邻分类算法和随机Hough变换理论,对哈密瓜这类椭圆形农产品的大小分级方法进行研究。结果表明:1)哈密瓜边缘轮廓近似椭圆形,所测出的长短轴半径,可以作为椭圆形哈密瓜大小分级的新标准;2)通过试验测定,对于白色背景的哈密瓜,最近邻分类算法可以提取出较为完整的边缘轮廓;3)随机Hough变换可以在边缘轮廓不完整且有随机噪声干扰的情况下,检测出任意曲率的哈密瓜边缘轮廓的近似椭圆;4)与椭圆形哈密瓜的半径的真实值相比,本改进算法识别值的相对误差小于6%;5)当哈密瓜处在不同倾斜状态时,如0°、45°、90°、135°,本改进算法仍可以准确测得其长短轴半径。本改进算法还可以推广到其他椭圆形和类椭圆形农产品的大小分级中。

Size classification of elliptical agricultural products based on improved Random Hough Transform

In order to solve the classification problem of elliptical agricultural products,Nearest Neighbor classification algorithm and Random Hough Transform theory are used to study the size classifying method of ellipse agricultural products,such as cantaloupe.The results show that:1) The radius of the long and short axis measured by the approximate ellipse of the cantaloupe edge contour can be used as a new standard for the size classification of the elliptical cantaloupe;2) Through experiment testing,for the cantaloupe with white background,the Nearest Neighbor classification algorithm can extract the almost complete edge contour;3) Random Hough Transform can detect the approximate ellipse of elliptical cantaloupe edge contour with arbitrary curvature under incomplete edge contour and random noise interference;4) Compared with the true value of the elliptical shape agricultural product,the relative error of the improved algorithm is less than 6%;5) When the cantaloupe is in different inclination states (such as 0°, 45°, 90° and 135°),the improved algorithm still can accurately measure its long and short axis radius.The improved algorithm can also be extended for the size classification of other elliptical and approximately oval agricultural products.