Fuente: WIPO "tobacco agriculture" The invention discloses a tobacco leaf classification method based on spectrum and machine vision coupling. The tobacco leaf classification method comprises the steps of collecting near infrared spectrum values and images of tobacco leaves through a near infrared spectrometer and a camera; removing the background of the acquired image, reducing the noise, calculating the average value of the nearinfrared spectrum points of the tobacco leaves, and eliminating the influence of uneven distribution of tobacco leaf particles on the average value; extracting image features; performing dimension reduction processing on the image features and the near infrared spectrum to obtain main features; fusing the main features and processing the main features by adopting a normalization method; creating agrading model, dividing the samples into a training set and a verification set, and training and classifying the model to construct a model; importing the fused pre-classified tobacco leaf features into a classification model for discrimination so as to output a maturity judgment result; and a sorting device or a worker classifies the tobacco leaves according to the output maturity judgment result. The tobacco maturity can be automatically recognized and judged, classified collection can be guided or controlled, and the method has the advantages of being accurate in classification, high in automation degree and not prone to damage the tobacco.