Small sample hyperspectral image classification method and system based on conduction type learning

The invention relates to the technical field of remote sensing image processing, in particular to a small sample hyperspectral image classification method and system based on conduction type learning, and the method comprises the steps: constructing a hyperspectral image classification model, training the hyperspectral image classification model through the data in a source domain data set and a target domain data set, and obtaining a hyperspectral image classification model; inputting a to-be-classified hyperspectral image into the trained hyperspectral image classification model, continuously optimizing the relationship between the features through an iteration mode, generating a prototype of each category of features, and carrying out classification according to the prototype corresponding to each category of features and the distance measurement of the features of the to-be-classified hyperspectral image data. And obtaining a hyperspectral image classification result according to the classification result