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 Experiment Video

Updated: Aug 16, 2025

Neuroimaging-Guided TMS–EEG for Real-Time Cortical Network Mapping
09:55

Neuroimaging-Guided TMS–EEG for Real-Time Cortical Network Mapping

Published on: June 13, 2025

962

TM-Net: A Neural Net Architecture for Tone Mapping.

Graham Finlayson1, Jake McVey1

  • 1School of Computing Sciences, University of East Anglia, Norwich Research Park, Norwich NR4 7TJ, UK.

Journal of Imaging
|December 22, 2022
PubMed
Summary

Contrast Limited Histogram Equalization (CLHE) can be formulated as a deep neural network. Training a 2-layer network significantly speeds up CLHE computation while maintaining visual accuracy.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Effects of exercise and exercise timing on energy intake and appetite control: a randomised crossover trial in people with overweight or obesity with and without type 2 diabetes.

EBioMedicine·2026
Same author

Why we eat: Development and validation of a 7-factor Motivations for Eating Profile (MEP-7).

Appetite·2026
Same author

Effects of Non-Nutritive Sweeteners and Sweet Taste Exposure on Weight Management, Biomarkers of Health and Sweet Taste Preference-A Review of the Evidence from Recent European Consortia Studies.

Nutrients·2026
Same author

Associations of body composition and resting metabolic rate with homeostatic and hedonic components of appetite.

International journal of obesity (2005)·2026
Same author

Simple tone curves: theory and applications.

The Visual computer·2026
Same author

Short-Term Moderately High-Fat Diet Has No Effect on Physical Performance.

Medicine and science in sports and exercise·2026

Area of Science:

  • Computer Vision
  • Image Processing
  • Deep Learning

Background:

  • Tone mapping algorithms compress image dynamic range for better detail and aesthetics.
  • Contrast Limited Histogram Equalization (CLHE) is a widely used, albeit iterative, tone mapping method.

Purpose of the Study:

  • To reformulate CLHE as a deep neural network (TM-Net).
  • To accelerate CLHE computation using a fixed-depth neural network.
  • To demonstrate the neural network approach for other complex tone mappers.

Main Methods:

  • Exact formulation of CLHE as a deep neural network (TM-Net).
  • Training a fixed 2-layer TM-Net to approximate CLHE.
  • Applying the 2-layer TM-Net to a quadratic programming-based tone mapper.
Keywords:
Contrast Limited Histogram EqualizationHistogram Equalizationcontrast enhancementtone mappingunrolling

More Related Videos

Neuronavigation-guided Repetitive Transcranial Magnetic Stimulation for Aphasia
08:48

Neuronavigation-guided Repetitive Transcranial Magnetic Stimulation for Aphasia

Published on: May 6, 2016

12.3K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

603

Related Experiment Videos

Last Updated: Aug 16, 2025

Neuroimaging-Guided TMS–EEG for Real-Time Cortical Network Mapping
09:55

Neuroimaging-Guided TMS–EEG for Real-Time Cortical Network Mapping

Published on: June 13, 2025

962
Neuronavigation-guided Repetitive Transcranial Magnetic Stimulation for Aphasia
08:48

Neuronavigation-guided Repetitive Transcranial Magnetic Stimulation for Aphasia

Published on: May 6, 2016

12.3K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

603

Main Results:

  • CLHE can be represented as a deep neural network with 60+ layers.
  • A 2-layer TM-Net achieves up to 30x speedup for CLHE computation.
  • The 2-layer TM-Net accurately reproduces results from more complex tone mapping methods.

Conclusions:

  • Deep neural networks offer an efficient alternative for implementing CLHE.
  • A compact 2-layer network can effectively capture the essence of CLHE and other tone mappers.
  • This approach significantly accelerates image tone mapping without compromising visual quality.