Tobacco leaf classification method based on spectrum and machine vision coupling

Abstract

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.

Description

technical field [0001] The invention belongs to the technical field of tobacco, and in particular relates to a method for classifying tobacco leaves based on the coupling of spectrum and machine vision, which is accurate in classification, highly automated and not easy to damage the tobacco leaves. Background technique [0002] "Tobacco leaf was planted in China as early as before the Han Dynasty." my country is the world's largest producer of tobacco leaf, and tobacco is an important economic crop in my country. Tobacco farmers pick fresh tobacco leaves, they need to classify according to the different parts of the tobacco leaves in the plant, as well as according to the different maturity, size, water content, starch content and protein content of the fresh tobacco leaves, and tie the tobacco leaves of the same grade in bundles on the tobacco rods and tobacco leaves. On the rope, the leaves with small leaves or low water content are slightly densely woven, and the leaves w...

AI Technical Summary

Problems solved by technology

However, in order to ensure the accuracy of machine vision, it is often necessary to set up a special light source and a light hood to ensure the stability of the color of the captured image. Generally, an auxiliary sensor such as an independent photoelectric detector is also set up to determine the position of the tobacco leaves, so as to ensure that when taking pictures. The correct position of the tobacco leaves in the lens is not only complicated in structure and weak in environmental adaptability, but also takes a long time for auxiliary preparation, a large amount of data, and easily damages the tobacco leaves

Images