基于棋盘格的可变参照物叶面积测量方法研究

Research on leaf area measurement of variable reference based on checkerboards

为进一步提高在图像处理方面的叶片面积测量精度,提出一种基于棋盘格的可变参照物叶面积测量方法。首先利用智能手机拍摄叶片图像,进行叶片图像分割,根据叶片分割结果选择与其面积相近的棋盘格作为参照矩形,然后提取棋盘格亚像素级角点信息实现图像几何失真校正,通过比例关系计算叶面积。为验证方法的精确性,对已知面积的规则图形进行试验,本文方法平均误差最大值为0.23%;并以相对精确的坐标纸法作为标准测量方法,与固定面积参照物方法进行比较,随着叶片面积与参照矩形面积比的增大,测量误差增大,本文可变参照物方法测量平均误差最大为0.51%。试验结果表明,对不同叶面积的测量,本文方法测量精度在99%以上。

In order to improve the accuracy of leaf area measurement in image processing,a leaf area measurement method of variable reference is presented based on checkerboards.The measurement steps are mainly divided into image acquisition,image segmentation,corner detection,geometric distortion correction,and leaf area calculation.According to the results of leaf segmentation,the checkerboard with a similar area was selected as the reference rectangle,and the information of sub-pixel corner points of the checkerboard was extracted to correct the geometric distortion of the image.The average maximum error is 0.23%for the regular graph with a known area.The relatively accurate coordinate paper method is used as the standard measurement method.Compared with the fixed area reference,as the ratio of the leaf area to the reference rectangle area increases,the measurement error increases.When the leaf area is closer to the reference rectangle area,the measurement error becomes smaller.The maximum average measurement error of this system is 0.51%.The experimental results show that this method provides a new and practical way for the measurement of leaf area.