Method and device for automatically sorting tobacco leaves based on neural network

Abstract

The application provides a method and device for automatically sorting tobacco leaves based on a neural network. The method includes: collecting natural light pictures of training tobacco leaves, analyzing the natural light pictures according to preset tobacco leaf feature dimension information to obtain natural feature information data of training tobacco leaves; Tobacco leaves are subjected to spectral analysis to obtain the spectral feature information data of the training tobacco leaves; the natural feature information data of the training tobacco leaves and the spectral feature information data are corresponding, and the neural network training is performed to obtain the correlation model between the natural features of the tobacco leaves and the spectral features; according to the spectral feature information data Establish the spectral tobacco leaf grading strategy of tobacco leaves, and obtain the natural grading strategy of tobacco leaves based on the correlation model; obtain the natural image of the tobacco leaves to be sorted, analyze the natural characteristic information data of the tobacco leaves to be sorted, and compare with the natural grading strategy to obtain the tobacco leaves to be sorted Sorting level, sorting the tobacco leaves to be sorted according to the sorting level. The invention realizes intelligent, efficient, standardized and low-cost sorting of tobacco leaves.

Description

technical field [0001] The present application relates to the technical field of automatic control, in particular to a method and device for automatically sorting tobacco leaves based on a neural network. Background technique [0002] Tobacco leaf is a raw material for the tobacco industry and is an important economic crop. The planting area in my country is also very wide, and it occupies an important position in my country's agricultural production. The quality and production process of tobacco leaves will directly affect the quality of tobacco products made from tobacco leaves. In the process of planting tobacco leaves, due to the influence of different regional climates, environments, soils, tobacco leaf varieties, growing parts, planting methods, and baking and preservation processes, the quality of tobacco leaf raw materials varies greatly. [0003] Therefore, it is necessary to grade tobacco leaves of different qualities, and produce tobacco leaf products of differen...

AI Technical Summary

Problems solved by technology

[0006] The purpose of this application is to provide a method and device for automatically sorting tobacco leaves based on a neural network to solve the technical problems of non-standardized tobacco leaf sorting, poor sorting quality, low sorting efficiency, and high cost in the prior art

Images