基于高光谱成像技术的大米溯源研究

利用高光谱成像技术提取大米的光谱信息进行大米产地溯源研究。采用X-Y距离样本集算法（SPXY）进行训练集和测试集的划分，将1 000颗大米样本中800个为训练集，剩下200个为测试集。并采用主成分分析（PCA）法提取相关性较强的主成分光谱信息，进行数据降维。基于主成分分析法提取前4个主成分，并在贡献率最高的第4主成分基础上，结合支持向量机算法（SVM）建立大米产地溯源预测模型。研究得出训练集准确率可达96%，测试集平均准确率为79%。通过训练集和测试集的实验结果表明，高光谱成像技术可以对大米产地进行溯源，为大米产地快速、无损检测提供了一定思路和参考。

Research on rice traceability based on hyperspectral imaging technology

The spectral information of rice was extracted by hyperspectral imaging technology to study rice origin traceability. The training set and the test set were divided by the sample set partitioning based on joint X-Y distance (SPXY) algorithm, and the 800 of the 1 000 rice samples were divided into the training set, and the remaining 200 were as the test set. The more relevant principal components spectrum information was extracted by principal component analysis (PCA) method to reduce the data dimension. Based on the first four principal components extracted by PCA method, and on the basis of the fourth principal component with the highest contribution rate, combined with the support vector machine (SVM) algorithm, the rice origin traceability prediction model was established. The results showed that the accuracy of the training set reached 96%, and the average accuracy of the test set was 79%. The experimental results of the training set and the test set showed that hyperspectral imaging technology could trace the origin of rice, providing a certain idea and reference for rapid and non-destructive detection of rice origin.