Material Discrimination Algorithm Based on Hyperspectral Image

Abstract

Hyperspectral information can be used to express the material properties of objects, which has a strong effect on camouflage recognition. However, it is difficult to process it directly because of the huge hyperspectral image data. Therefore, this paper proposes a new band selection algorithm to achieve band selection by simulating visual perception. The subspace clustering self-attention adversarial network is constructed to realize the initial selection of band. According to the visual chromatic aberration principle, a model is constructed to determine the band that combines the strongest response intensity of a particular material, and then this band is selected as the final band, therefore realizing the algorithm of material demarcation in this way.

A Review of Performance Prediction Based on Machine Learning in Materials Science

“…For example, supervised machine learning is often used for classification or prediction. Image recognition is a typical example of supervised ML [ 27 , 28 , 29 ]. On the MNIST dataset, ML attempts to obtain a mapping relationship between pixels and labels.…”