基于颜色与纹理特征的苹果叶片含水率预测

Prediction of apple leaf moisture content based on color and texture features

    摘要
  • 摘要:
    目的 建立苹果叶片含水率的精准无损预测方法。
    方法 本研究采用工业相机获取叶片RGB图像，并分别从不同颜色空间下提取颜色特征和采用灰度共生矩阵(Grey-level co-occurrence matrix，GLCM)技术提取纹理特征。通过统计分析，确定了与叶片含水率显著相关的34个图像特征。为进一步提高模型效率与准确性，应用主成分分析(Principal component analysis，PCA)方法对这些相关特征进行了降维处理。基于降维后的数据，分别建立偏最小二乘回归(Partial least squares regression，PLSR)模型、随机森林(Random forest，RF)模型、卷积神经网络(Convolutional neural network，CNN)模型。
    结果 对于降维后的数据建立的数学模型，3个模型的预测集决定系数(R2P)分别为0.62、0.879、0.716，均方根误差(Root mean square error of prediction，RMSEP)分别为2.037、1.102、1.954，剩余预测偏差(Residual prediction deviation，RPD)分别为1.636、3.421、1.948。
    结论 该研究为苹果叶片含水率的快速无损检测提供了新方法，随机森林模型预测精度最优。

     

    Abstract:
    Objective To establish an accurate non-destructive prediction method for apple leaf moisture content.
    Methods In this study, an industrial camera was used to collect RGB images of apple leaves. Color features were extracted from multiple color spaces, and texture features were extracted by the Grey-level Co-occurrence Matrix (GLCM) technology. Statistical analysis was performed to screen out 34 image features significantly correlated with leaf moisture content. Principal Component Analysis (PCA) was adopted to reduce the dimensionality of the above correlated features for higher model efficiency and prediction accuracy. On the basis of dimension-reduced features, Partial Least Squares Regression (PLSR), Random Forest (RF) and Convolutional Neural Network (CNN) models were constructed respectively.
    Results For the three models built with dimension-reduced data, the coefficients of determination of prediction set (R2P) were 0.62, 0.879 and 0.716; the Root Mean Square Error of Prediction (RMSEP) were 2.037, 1.102 and 1.954; the Residual Prediction Deviation (RPD) were 1.636, 3.421 and 1.948 in sequence.
    Conclusion This study provides a novel method for rapid non-destructive detection of apple leaf moisture content, and the Random Forest model achieves the optimal prediction accuracy.

     

    • HTML全文
    • 参考文献(28)
    • 相关文章
    • 施引文献
  • 资源附件(0)

/

返回文章
返回