Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

IR Frequency Region: Fingerprint Region01:03

IR Frequency Region: Fingerprint Region

866
IR spectra are divided into two main regions: the diagnostic region and the fingerprint region. The diagnostic region of the spectrum lies above 1500 cm−1. The absorptions resulting from single-bond vibrations of the N–H, C–H, and O–H stretch at higher wavenumbers and appear on the left side of the spectrum. The stretching absorptions of the C≡C and C≡N occur between 2100–2300 cm−1. In contrast, those arising from stretching absorptions of the...
866

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Extrapolation Convolution for Data Prediction on a 2-D Grid: Bridging Spatial and Frequency Domains With Applications in Image Outpainting and Compressed Sensing.

IEEE transactions on neural networks and learning systems·2025
Same author

Technical Design of a Low-Latitude Satellite Constellation for Ocean Observation with a Focus on Hainan Province, China.

Sensors (Basel, Switzerland)·2025
Same author

Wave-Net: A Marine Raft Aquaculture Area Extraction Framework Based on Feature Aggregation and Feature Dispersion for Synthetic Aperture Radar Images.

Sensors (Basel, Switzerland)·2025
Same author

PolySegNet: improving polyp segmentation through swin transformer and vision transformer fusion.

Biomedical engineering letters·2024
Same author

A dual-encoder double concatenation Y-shape network for precise volumetric liver and lesion segmentation.

Computers in biology and medicine·2024
Same author

Optimized efficient attention-based network for facial expressions analysis in neurological health care.

Computers in biology and medicine·2024

Related Experiment Video

Updated: Jun 25, 2025

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals
00:07

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Published on: August 22, 2019

8.0K

Discriminating Spectral-Spatial Feature Extraction for Hyperspectral Image Classification: A Review.

Ningyang Li1, Zhaohui Wang1, Faouzi Alaya Cheikh2

  • 1Faculty of Computer Science and Technology, Hainan University, Haikou 570228, China.

Sensors (Basel, Switzerland)
|May 25, 2024
PubMed
Summary
This summary is machine-generated.

Deep learning methods enhance hyperspectral image (HSI) classification by improving spectral-spatial feature discrimination. This review systematically summarizes techniques for feature extraction and optimization to overcome limitations of traditional machine learning.

Keywords:
discriminating spectral–spatial featuresfeature extractionfeature optimizationhyperspectral image classification

More Related Videos

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters
07:05

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

2.4K
Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification
07:47

Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification

Published on: February 14, 2018

11.2K

Related Experiment Videos

Last Updated: Jun 25, 2025

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals
00:07

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Published on: August 22, 2019

8.0K
Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters
07:05

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

2.4K
Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification
07:47

Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification

Published on: February 14, 2018

11.2K

Area of Science:

  • Remote Sensing
  • Computer Vision
  • Spectral Imaging

Background:

  • Hyperspectral images (HSIs) offer rich spectral and spatial data for land cover classification.
  • Traditional machine learning methods struggle with HSI classification due to band redundancy and complex spatial structures.
  • Deep learning approaches have emerged to better discriminate spectral-spatial features in HSIs.

Purpose of the Study:

  • To systematically review crucial factors for discriminating spectral-spatial features in hyperspectral image classification.
  • To explore techniques for feature extraction and feature optimization in HSI classification.
  • To discuss current limitations and future challenges in HSI classification.

Main Methods:

  • Summarizing techniques for spectral feature discrimination based on HSI characteristics and model architectures.
  • Illustrating methods for spatial feature and spectral-spatial feature discrimination.
  • Detailing techniques for feature optimization to adjust inter-class distances in classification space.

Main Results:

  • Identification of key techniques in feature extraction to enhance spectral, spatial, and combined features.
  • Explanation of feature optimization strategies for improved class separability.
  • Discussion of the characteristics and limitations of current feature discrimination techniques.

Conclusions:

  • Deep learning offers significant advancements in hyperspectral image classification by effectively extracting and optimizing spectral-spatial features.
  • Further research is needed to address limitations and challenges in feature discrimination for enhanced HSI classification accuracy.
  • Systematic summarization provides a valuable resource for researchers in the field of hyperspectral image analysis.