Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

IR Frequency Region: Fingerprint Region

IR Frequency Region: Fingerprint Region

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...

You might also read

Related Articles

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

Sort by

Same author

A model for classifying information objects using neural networks and fuzzy logic.

Scientific reports·2025

Same author

Spatial point patterns generation on remote sensing data using convolutional neural networks with further statistical analysis.

Scientific reports·2022

Same author

Artificial Intelligence and Its Application to Minimal Hepatic Encephalopathy Diagnosis.

Journal of personalized medicine·2021

See all related articles

Search research articles

Related Experiment Video

Updated: Jul 11, 2025

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Published on: August 22, 2019

Features extraction from multi-spectral remote sensing images based on multi-threshold binarization.

Bohdan Rusyn^1,2, Oleksiy Lutsyk³, Rostyslav Kosarevych¹

¹Department of Remote Sensing Information Technologies, Karpenko Physico-Mechanical Institute, NAS of Ukraine, Lviv, Ukraine.

Scientific Reports

|November 11, 2023

Summary

This study introduces multi-threshold binarization for faster remote sensing image classification. The new method enhances accuracy on small datasets and significantly reduces training and inference times compared to deep CNN models.

More Related Videos

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

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

Published on: June 18, 2021

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

Related Experiment Videos

Last Updated: Jul 11, 2025

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Published on: August 22, 2019

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

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

Published on: June 18, 2021

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

Area of Science:

Computer Science
Remote Sensing
Machine Learning

Background:

Deep Convolutional Neural Networks (CNNs) face limitations in real-time applications due to computational demands.
Remote sensing image classification requires efficient models for timely analysis.

Purpose of the Study:

To propose an efficient solution for real-time remote sensing image classification.
To overcome the computational limitations of deep CNN models.

Main Methods:

Utilizing multi-threshold binarization on multi-spectral remote sensing images.
Extracting discriminative features for classification.
Comparing the proposed approach with ResNet and Ensemble CNN models in terms of accuracy and training time.

Main Results:

The proposed approach demonstrates superior accuracy on small datasets.
It maintains a comparable recall score to deep CNN models on larger datasets.
Achieves approximately 5 times lower training and inference time across all dataset sizes.

Conclusions:

Multi-threshold binarization offers a computationally efficient alternative for remote sensing image classification.
The method balances accuracy with significant speed improvements, making it suitable for real-time applications.