Tobacco leaf grading method based on Faster R-CNN network

Abstract

The invention relates to the technical field of computer image processing, in particular to a tobacco leaf grading method based on a Faster R-CNN network. The method comprises the following steps: (1) collecting tobacco leaf images and establishing a tobacco leaf image data set of tobacco leaf grade classification; (2) on the basis of a VGG16 network model, adjusting parameters of the model, improving a region-of-interest pool of the model into a region-of-interest (ROI) Align, removing three convolutional layers including an eighth layer, a twelfth layer and a fifteenth layer, introducing an Inception network structure, and establishing a Faster R-CNN network model; and (3) taking a deep learning framework caffe as an experimental platform, and training the tobacco leaf image data set by using a Faster R-CNN network. The improved tobacco leaf grading algorithm has the advantages of high network convergence speed in classifier training, high recognition rate, high recognition speed and the like in recognition.

Description

technical field [0001] The invention relates to the technical field of computer image processing, in particular to a method for grading tobacco leaves based on a Faster R-CNN network. Background technique [0002] Tobacco products are the main agricultural economic crops in my country, and the quality evaluation and grading of tobacco leaves play a vital role. Tobacco leaf is one of the main raw materials of tobacco products, and its quality is the key to the stability of tobacco products in the later stage. Using computer vision to classify tobacco leaves can not only solve the shortcomings of traditional manual grading methods such as high labor intensity, strong subjectivity, and low work efficiency, but also stabilize the grading accuracy and grading pass rate. However, the existing tobacco leaf grading methods have a strong dependence on image acquisition, preprocessing and feature extraction, especially for images with inconspicuous features. [0003] With the develo...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the deficiencies of the prior art, the present invention provides a tobacco leaf grading method based on the Faster R-CNN network, which solves the problem of low grading accuracy caused by too similar characteristics between different grades of tobacco leaf parts and insufficient data sets, and the classification of tobacco leaves. Technical issues such as recognition accuracy

Images