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

Photoreceptors and Visual Pathways01:22

Photoreceptors and Visual Pathways

6.1K
At the molecular level, visual signals trigger transformations in photopigment molecules, resulting in changes in the photoreceptor cell's membrane potential. The photon's energy level is denoted by its wavelength, with each specific wavelength of visible light associated with a distinct color. The spectral range of visible light, classified as electromagnetic radiation, spans from 380 to 720 nm. Electromagnetic radiation wavelengths exceeding 720 nm fall under the infrared category,...
6.1K
UV–Vis Spectroscopy: Woodward–Fieser Rules01:29

UV–Vis Spectroscopy: Woodward–Fieser Rules

24.7K
UV–Visible absorption spectra of conjugated dienes arise from the lowest energy π → π* transitions. The light-absorbing part of the molecule is called the chromophore, and the substituents directly attached to the chromophore are called auxochromes. A strong correlation exists between the absorption maxima, λmax, and the structure of a conjugated π system. The Woodward–Fieser rules predict the value of λmax for a given...
24.7K

You might also read

Related Articles

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

Sort by
Same author

Life Cycle Assessment of Micro and Macro Algae Products.

Methods in molecular biology (Clifton, N.J.)·2026
Same author

A Comparative Evaluation of Super-Resolution Methods for Spectral Images Using Pretrained RGB Models.

Sensors (Basel, Switzerland)·2026
Same author

Trends in Snapshot Spectral Imaging: Systems, Processing, and Quality.

Sensors (Basel, Switzerland)·2025
Same author

Spectral Reconstruction from RGB Imagery: A Potential Option for Infinite Spectral Data?

Sensors (Basel, Switzerland)·2024
Same author

Relationship between reflectance and degree of polarization in the VNIR-SWIR: A case study on art paintings with polarimetric reflectance imaging spectroscopy.

PloS one·2024
Same author

Raw Spectral Filter Array Imaging for Scene Recognition.

Sensors (Basel, Switzerland)·2024

Related Experiment Video

Updated: Jul 24, 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

8.1K

Impact of Exposure and Illumination on Texture Classification Based on Raw Spectral Filter Array Images.

Omar Elezabi1, Sebastien Guesney-Bodet1, Jean-Baptiste Thomas1

  • 1Colourlab, Department of Computer Science, Norwegian University of Science and Technology (NTNU), 2815 Gjøvik, Norway.

Sensors (Basel, Switzerland)
|July 8, 2023
PubMed
Summary

This study explores texture classification using raw Spectral Filter Array (SFA) camera images, bypassing traditional demosaicing. A Convolutional Neural Network (CNN) demonstrated superior performance over Local Binary Patterns, even with limited data and varying conditions.

Keywords:
convolutional neural networksspectral filter arraytexture 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

2.5K
Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images
11:49

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

9.4K

Related Experiment Videos

Last Updated: Jul 24, 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

8.1K
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

2.5K
Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images
11:49

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

9.4K

Area of Science:

  • Computer Vision
  • Image Processing
  • Machine Learning

Background:

  • Spectral Filter Array (SFA) cameras offer portable spectral imaging, but texture classification relies on demosaicing.
  • Demosaicing quality impacts texture classification accuracy in SFA imaging.
  • Directly analyzing raw SFA images could improve texture classification robustness.

Purpose of the Study:

  • To investigate texture classification methods applied directly to raw Spectral Filter Array (SFA) images.
  • To compare the performance of a Convolutional Neural Network (CNN) against the Local Binary Pattern (LBP) method for raw SFA image texture classification.
  • To evaluate the influence of integration time and illumination on classification performance.

Main Methods:

  • Training a Convolutional Neural Network (CNN) on raw SFA images from the HyTexiLa database.
  • Comparing CNN performance against the Local Binary Pattern (LBP) method.
  • Conducting experiments with real SFA images, not simulated data.
  • Analyzing the impact of integration time and illumination levels on classification accuracy.

Main Results:

  • The Convolutional Neural Network (CNN) significantly outperformed the Local Binary Pattern (LBP) method for texture classification.
  • The CNN achieved high performance even with a small amount of training data.
  • The CNN demonstrated adaptability to varying environmental conditions, including illumination and exposure settings.
  • Feature analysis revealed the CNN's ability to recognize diverse shapes, patterns, and marks within textures.

Conclusions:

  • Direct texture classification from raw SFA images using CNNs is a viable and effective approach.
  • CNNs offer superior robustness and adaptability compared to traditional methods like LBP for SFA texture analysis.
  • This method enhances texture classification accuracy and reliability, especially under challenging environmental conditions.