Loading [MathJax]/extensions/MathZoom.js
Dimensionality Reduction and Classification of Hyperspectral Image via Multistructure Unified Discriminative Embedding | IEEE Journals & Magazine | IEEE Xplore

Dimensionality Reduction and Classification of Hyperspectral Image via Multistructure Unified Discriminative Embedding


Abstract:

Graph can achieve good performance to extract the low-dimensional features of hyperspectral image (HSI). However, the present graph-based methods just consider the indivi...Show More

Abstract:

Graph can achieve good performance to extract the low-dimensional features of hyperspectral image (HSI). However, the present graph-based methods just consider the individual information of each sample in a certain characteristic, which is very difficult to represent the intrinsic properties of HSI for the complex imaging condition. To better represent the low-dimensional features of HSI, we propose a multistructure unified discriminative embedding (MUDE) method, which considers the neighborhood, tangential, and statistical properties of each sample in HSI to achieve the complementarity of different characteristics. In MUDE, we design the intraclass and interclass neighborhood structure graphs with the local reconstruction structure of each sample; meanwhile, we also utilize the adaptive tangential affine combination structure to construct the intraclass and interclass tangential structure graphs. To further enhance the discriminating performance between different classes, we consider the influence of the statistical distribution difference for each sample to develop an interclass Gaussian weighted scatter model. Then, an embedding objective function is constructed to enhance the intraclass compactness and the interclass separability and obtain more discriminative features for HSI classification. Experiments on three real HSI datasets show that the proposed method can make full use of the structure information of each sample in different characteristics to achieve the complementarity of different features and improve the classification performance of HSI compared with the state-of-the-art methods.
Article Sequence Number: 5517916
Date of Publication: 16 November 2021

ISSN Information:

Funding Agency:


I. Introduction

Hyperspectral image (HSI) contains hundreds of channels captured by imaging spectrometer under narrow and continuous electromagnetic spectrums covering from visible light to infrared light [1]–[3]. In HSI intelligent interpretation, each pixel is considered as a high-dimensional vector, which provides rich characteristic information of target objects [4]–[6]. Since different target objects contain different characteristic information, the type of each pixel can be recognized according to the differences of high-dimensional vectors [7], [8]. However, there is a large amount of redundant information in high-dimensional HSI data, which will have an adverse effect on the discriminant performance of features for HSI classification task [9]–[11].

References

References is not available for this document.