基于数字图像数据的烤烟成熟度指数研究

Study on maturity index of flue-cured tobacco leaves based on digital image processing technique

为量化判别烤烟鲜烟叶成熟度,提出了一种基于数字图像处理的成熟度指数计算方法。首先对烟叶数字图像进行预处理去除背景,并进行马赛克压缩;其次分析烟叶图像中与烤烟鲜烟叶成熟度相关的RGB变量,从中找出一个代表性的表征变量转换为成熟度值,结合人工感官判断准则,把成熟度值的范围限定在0-10之间;然后用成熟度值将RGB 3基色值图像转换为单值图像,最后利用TRIMMEAN函数进行去极值求均值处理获得整片烤烟鲜烟叶的成熟度指数。通过实验验证,该方法计算出的成熟度指数与人工感官识别的烟叶经验成熟度有很好的关联度。因此这种可实时实现成熟度智能量化的方法可以用来判别和比较烟叶的成熟度,有望据此设计一个快速高效的烤烟鲜烟叶成熟度自动检测系统。

To quantify the maturity of flue-cured tobacco leaves,a maturity index based on image processing is proposed.Digital images of different tobacco leaves are obtained and processed by Mosaic algorithm and TRIMMEAN functions.The maturity variable MaR is found by study different factors R,G,B,color value,R＋G＋B,R＋G,R＋B and G＋B which infecting tobacco leaf maturity.Better proportion rates to accurately quantify maturity of tobacco leaves are given by researching different proportion rates of Mosaic and TRIMMEAN.Maturity values of white leaves（extreme conditions） are defined as 10.The test results of tobacco leaves for tobacco leaves with different ripe degrees and whole plants show that the maturity index proposed in this paper is identical with sensory recognition and experience of maturity.Therefore,this maturity index can be used to determine comparative leaf maturity.