Semi-supervised hyperspectral data analysis method based on two-stream conditional adversarial generative network

Abstract

The invention relates to a semi-supervised hyperspectral data analysis method based on a two-stream conditional confrontation generation network, comprising steps: S1, acquiring hyperspectral sample data; S2, image segmentation, and embedding each sample into a three-dimensional data block; S3, dividing training Sample set and prediction sample set, and perform data preprocessing, and the prediction sample set is also added to training as unlabeled samples; S4, build a two-stream conditional confrontation generation network, including a two-stream structure generator network, discriminator network and regressor network, For the extraction and fusion of spectral features and spatial morphology features, the generator network is used to generate samples, the discriminator network is used to distinguish the authenticity of samples, and the regressor network is used to quantitatively analyze the regression target value Regression calculation; S5, constructing the loss function of the generator network, the discriminator network and the regressor network; S6, training the confrontation generation network; S7, using the trained confrontation generation network to obtain the regression target value of the quantitative analysis of the prediction sample set.

Description

technical field [0001] The invention relates to the technical field of hyperspectral detection, in particular to a semi-supervised hyperspectral data analysis method based on a two-stream conditional confrontation generation network. Background technique [0002] Hyperspectral-based quantitative analysis technology has a wide range of application scenarios, including food adulteration detection, fruit sugar content detection, microbial content detection, organic matter content detection, etc. [0003] At present, the commonly used quantitative analysis methods of hyperspectral data include partial least squares regression (PLSR), least squares support vector machine (LS-SVM), multiple linear regression (MLR), etc. [0004] The inventor found in the research that there are two main problems in the current hyperspectral quantitative analysis methods: (1) most of the quantitative analysis methods use the average spectrum to model, such as PLS and LS-SVM, which fail to make full...

AI Technical Summary

Problems solved by technology

[0004] The inventor found in the research that there are two main problems in the current hyperspectral quantitative analysis methods: (1) most of the quantitative analysis methods use the average spectrum to model, such as PLS and LS-SVM, which fail to make full use of the hyperspectral The spatial information contained in the spectral data, how to effectively extract and fuse the spectral features and spatial morphology features in the hyperspectral data is an urgent need for further research.

(2) Existing hyperspectral data analysis methods, in actual application scenarios, the number of training samples is limited, and the accuracy and generalization ability of the model are poor

Images