基于计算机视觉的三七主根质量的分级方法

选取干燥后的三七主根样本110个,运用计算机视觉技术获取三七主根样本图像,对图像进行灰度化、二值化以及形态学运算,提取长、宽、投影面积等特征值。结果表明,三七主根的形状可分为锥形和瘤形,分别对2种主根建立投影面积和质量的关系预测模型,三七主根的质量和投影面积呈线性相关,锥形三七主根与瘤形三七主根投影面积和质量预测模型的决定系数R2分别为0.984 9和0.986 6。采用十折交叉验证法对质量预测模型进行验证,锥形三七主根质量误差均值0.334 8 g;瘤形三七主根质量误差均值0.494 9 g。

Quality classification method ofPanax notoginseng taproot based on computer vision

In this study, 110 driedPanax notoginseng were selected as the test samples. Computer vision technology was used to obtain the images ofPanax notoginseng taproot, which were deal with gray, binary and morphological to extract the length, width and projection area was ed after preprocess.The prediction models were built to calculate the projection area and the weight for conePanax notoginseng and nodulePanax notoginseng, respectively. The results showed that the weight of mainroot was linely correlated with the projection area. The determination coefficients of conePanax notoginseng and nodulePanax notoginseng were 0.984 9 and 0.986 6, respectively. The quality prediction model was verified by 10-fold cross-validation method. The average error was 0.3348 g and 0.494 9 g for conePanax notoginseng and nodulePanax notoginseng, respectively.