Tobacco leaf grading method based on hyperspectral image and deep learning algorithm

Abstract

The invention discloses a tobacco leaf grading method based on a hyperspectral image and a deep learning algorithm. The tobacco leaf grading method comprises steps of 1, obtaining hyperspectral image data of a tobacco leaf sample to be measured, 2, performing high level characteristic extraction on the image data to perform dimension reduction, and 3, performing classification on obtained image information and spectral information. A hardware platform of a hyperspectral imaging system comprises a light source, a light splitting module, an area array CCD detector and a computer provided with an image collection card; spectral information can be obtained while the imaging system is utilized to perform image information collection, separate collection is not needed and collection time is shortened; in the step 2, a convolutional neural network is utilized to perform pre-processing and then a deep belief network is utilized to perform characteristic extraction; in the step 3, a Sofmax layer is added on the top layer and obtained characteristics are inputted into a softmax regression classifier to realize classification. The tobacco leaf grading method based on the hyperspectral image and deep learning can maximally achieve lossless grading, accurately divides a tobacco leaf grade, and ensures benefits of a purchasing party.

Description

technical field [0001] The invention relates to a method for grading tobacco leaves, in particular to a method for grading tobacco leaves based on hyperspectral images and deep learning algorithms. Background technique [0002] At present, most people use infrared or near-infrared spectroscopy to classify tobacco leaves, but there is no research on tobacco leaf classification technology using hyperspectral images combined with deep learning methods. [0003] In the literature of "Computer Application Research" Liu Jianwei and others, we know that the deep learning architecture is composed of multiple layers of nonlinear computing units, and the output of each lower layer is used as the input of the higher layer, which can learn effective feature representation from a large amount of input data. , the learned high-level representation contains a lot of structural information of the input data, which is a good way to extract representation from the data and can be used in spec...

AI Technical Summary

Problems solved by technology

A large number of studies have proved that the deep belief network can solve the traditional back propagation algorithm to train the multi-layer neural network with slow convergence speed and easy to fall into local optimum.

Images