Automatic classification of tobacco leaves based on NIR spectroscopy technology and NNLS sparse coding algorithm

Abstract

A tobacco leaf automatic classification method based on near-infrared (NIR) spectroscopy technology and non-negative least squares (NNLS) sparse coding algorithm is put forward by the paper. The method uses all the NIR spectral data of training samples to make up a data dictionary of the sparse representation (SR) and the NIR spectral data of test samples are represented by the sparsest linear combinations of the dictionary by NNLS sparse coding algorithm. Then the regression residual of the test sample to each class is computed, and finally it is assigned to the class with the minimum residual. The effectiveness of the NNLS method is compared with K-Nearest Neighbor (KNN) and Particle Swarm Optimization-Support Vector Machine (PSO-SVM) algorithms, the results show that the classification accuracy of the proposed method is higher and it is more efficient. The method proposed by the paper can accurately recognize different classes of tobacco leaves and it provides a new technology of quality class evaluation in the tobacco leaf purchasing.