Tensor Nuclear Norm Based Matrix Regression Based Projections for Feature Extraction of Hyperspectral Images

Hong Qiu, Heng Jin, Renfang Wang*, Xiufeng Liu, Guang Gao

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

With high spectral resolution, hyperspectral image(HSI) data will result in the Hughes phenomenon, which brings a huge challenge to hyperspectral image classification(HIC). Feature extraction can be applied to address this problem. But several traditional methods often ignore the spatial structure information of HSI data. In this paper, we propose a tensor nuclear norm based matrix regression based projections(TNMRP) for feature extraction of hyperspectral images. Firstly, TNMRP preprocesses the data by a filling method. Then, it automatically builds the graph of block-tensor samples and uses the optimal sparse coding coefficients to obtain the weight matrix. Finally, based on tensor representation, TNMRP calculates the optimal projection matrix. Experiments of classification on Indian Pines and Pavia University databases demonstrate the effectiveness of our proposed method.

Original languageEnglish
Title of host publicationProceedings of the 2023 26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023
Number of pages6
PublisherInstitute of Electrical and Electronics Engineers Inc.
Publication date2023
Pages1037-1042
ISBN (Electronic)9798350331684
DOIs
Publication statusPublished - 2023
Event26th International Conference on Computer Supported Cooperative Work in Design - Rio de Janeiro, Brazil
Duration: 24 May 202326 May 2023
Conference number: 26

Conference

Conference26th International Conference on Computer Supported Cooperative Work in Design
Number26
Country/TerritoryBrazil
CityRio de Janeiro
Period24/05/202326/05/2023
SponsorIEEE, Kunming University, Université de technologie de Compiègne, Yunnan University, Zhejiang University
SeriesProceedings of the 2023 26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

Keywords

  • Classification
  • Feature Extraction
  • Hyperspectral Image(HSI)
  • NMRP
  • Tensor
  • TNMRP

Fingerprint

Dive into the research topics of 'Tensor Nuclear Norm Based Matrix Regression Based Projections for Feature Extraction of Hyperspectral Images'. Together they form a unique fingerprint.

Cite this