An online grading method of tobacco leaves based on deep learning algorithm

Abstract

The present invention relates to an online tobacco grading method based on a deep learning algorithm. Through a complete tobacco leaf grading system, it can be classified from the front and back sides to the three classifications of positive tobacco, green tobacco and miscellaneous tobacco, and then to the classification of positive tobacco. It is suitable for Online grading; background mask based on supervised learning method, compared with traditional algorithms, the accuracy of background processing is higher; all front tobacco leaves are used for classification and grading, and the grading characteristics of tobacco leaves are more reflected on the front tobacco leaves, using full front tobacco leaves Classification and grading are more rigorous and scientific and have higher accuracy; the GoogLeNet model is used to classify positive group smoke, and higher grading accuracy can be obtained with more convolutions and deeper network layers. The invention can completely remove green smoke and miscellaneous smoke quickly, non-destructively and online, accurately classify the grades of the regular tobacco leaves, and ensure that the interests of all aspects of the purchase are not lost.

Description

technical field [0001] The invention relates to an online tobacco grading method, in particular to an online tobacco grading method based on a deep learning algorithm. Background technique [0002] At present, many researchers use infrared spectroscopy or image processing technology combined with traditional machine vision algorithms, such as support vector machines, to classify tobacco leaves. There are few reports on the online classification of tobacco leaves based on RGB images combined with deep learning methods. [0003] The concept of deep learning originated from the study of artificial neural networks. It was first proposed by Hinton et al. in 2006. Based on the deep belief network (DBN), a non-supervised greedy layer-by-layer training algorithm is proposed, which brings hope to solve the optimization problems related to the deep structure, and then a multi-layer autoencoder deep structure is proposed. [0004] In addition, the convolutional neural network propose...

AI Technical Summary

Problems solved by technology

[0002] At present, many researchers use infrared spectroscopy or image processing technology combined with traditional machine vision algorithms, such as support vector machines, to classify tobacco leaves. There are few reports on the online classification of tobacco leaves based on RGB images combined with deep learning methods.

Images