Rapid and Automatic Classification of Tobacco Leaves Using a Hand-Held DLP-Based NIR Spectroscopy Device

A hand-held near infrared (NIR) spectroscopy device is much more convenient than a traditional desktop NIR instrument. Thus, it is more suitable for the practical application. An automatic and rapid tool for grading tobacco leaves on the spot using a hand-held digital light processing (DLP)-based NIR spectroscopy device is proposed in this paper. Firstly, the spectral data of the samples is scanned with a hand-held NIR device directly from the tobacco leaves without any samples preparation procedures. Then, the training model of different classes is built and the class of each test sample is predicted by using sparse representation classification (SRC) algorithm. Comparing with the traditional linear discriminant analysis (LDA) and support vector machine (SVM) algorithms, the classification accuracy of SRC method is the highest and has the least computation time. The results show that hand-held NIR spectroscopy technology could be a novel classification tool for grading tobacco leaves in the purchasing on the spot.手持式近红外光谱（near infrared spectroscopy, NIR）设备相较于传统台式近红外仪器更为便捷，因此更适配实际应用场景。本文提出了一款基于手持式数字光处理（Digital Light Processing, DLP）近红外光谱设备的工具，可在现场自动、快速完成烟叶分级工作。首先，研究人员可直接使用该手持式近红外光谱设备对烟叶样本进行光谱数据扫描，无需任何样本前处理流程。随后，构建不同类别的训练模型，并利用稀疏表示分类（Sparse Representation Classification, SRC）算法对每个测试样本的类别进行预测。与传统线性判别分析（Linear Discriminant Analysis, LDA）及支持向量机（Support Vector Machine, SVM）算法相比，SRC方法的分类准确率最高，且计算耗时最短。研究结果表明，手持式近红外光谱技术可作为一种新型分类工具，应用于现场收购环节的烟叶分级工作。