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

Color Vision

Color Vision

Color perception begins in the retina, the light-sensitive layer at the back of the eye. Two main theories explain how colors are seen: the trichromatic theory and the opponent-process theory. The trichromatic theory, proposed by Thomas Young in 1802 and extended by Hermann von Helmholtz in 1852, suggests that color vision is based on three types of cone receptors in the retina. These cones are sensitive to different but overlapping ranges of wavelengths corresponding to red, blue, and green.

You might also read

Related Articles

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

Sort by

Same author

The landscape of pruning for large language models: A systematic review and unified taxonomy.

Neural networks : the official journal of the International Neural Network Society·2026

Same author

Effects of adding R-BoT + plus verticalization-based robotic locomotor training to conventional rehabilitation in patients with subacute stroke: a randomized controlled trial.

Journal of neuroengineering and rehabilitation·2026

Same author

Comparison of Annual Dynamic Abbreviated MRI and Biannual Ultrasound for HCC Surveillance in a High-Risk Group: Two-Center Cohort Study.

Liver cancer·2026

Same author

Incidence and risk factors of post-transplant diabetes mellitus after kidney transplantation: a systematic review and meta-analysis.

Frontiers in endocrinology·2026

Same author

Diagnostic Accuracy of Extracellular versus Hepatobiliary Contrast-enhanced MRI in LI-RADS Nonradiation Treatment Response Algorithm Version 2024.

Radiology·2026

Same author

Spectral-Adaptive Modulation Networks for Visual Perception.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Hidden Data Recovery and Forecasting via Next-Generation Reservoir Computing With Multiscale Delay Selection.

IEEE transactions on neural networks and learning systems·2026

Same journal

CAFF-CIL: Causality-Aware Freedom Forgetting Approach for Class-Incremental Learning.

IEEE transactions on neural networks and learning systems·2026

Same journal

Harmonic Autoencoding Framework for Multiple Tasks in Magnetic Particle Imaging Reconstruction.

IEEE transactions on neural networks and learning systems·2026

Same journal

A Survey on Human-Centric Voice-Face Multimodal Learning.

IEEE transactions on neural networks and learning systems·2026

Same journal

Vision-Assisted Foundation Model for Solving Multitask Vehicle Routing Problems.

IEEE transactions on neural networks and learning systems·2026

Same journal

FP3O: Enabling Proximal Policy Optimization in Multiagent Cooperation With Parameter-Sharing Versatility.

IEEE transactions on neural networks and learning systems·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Apr 19, 2026

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

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

Published on: December 15, 2023

Region-Based Object Recognition by Color Segmentation Using a Simplified PCNN.

Yuli Chen, Yide Ma, Dong Hwan Kim

IEEE Transactions on Neural Networks and Learning Systems

|December 11, 2014

Summary

This summary is machine-generated.

This study introduces a region-based object recognition (RBOR) method using a simplified pulse-coupled neural network (SPCNN) for robust identification in complex scenes. The SPCNN-RBOR approach effectively handles variations, occlusion, and clutter for both textured and less-textured objects.

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

Published on: July 11, 2025

Related Experiment Videos

Last Updated: Apr 19, 2026

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

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

Published on: December 15, 2023

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

Published on: July 11, 2025

Area of Science:

Computer Vision
Artificial Intelligence
Image Processing

Background:

Object recognition in complex scenes remains challenging due to variations in lighting, occlusion, and clutter.
Traditional feature-based methods struggle with background information when keypoints are near object boundaries.

Purpose of the Study:

To propose a novel region-based object recognition (RBOR) method for accurate object identification in complex real-world scenes.
To enhance object recognition robustness against various environmental and object-related challenges.

Main Methods:

Color image segmentation using a simplified pulse-coupled neural network (SPCNN) for both model and test images.
A novel image segmentation strategy groups synchronously firing pixels across transformed color channels (normalized RGB and opponent color spaces).
Region-based matching with adaptive thresholds for outlier removal, cluster formation, and refinement.

Main Results:

The proposed simplified pulse-coupled neural network-region-based object recognition (SPCNN-RBOR) method demonstrates robustness in diverse complex variations.
The method effectively handles partial occlusion and highly cluttered environments.
SPCNN-RBOR outperforms current feature-based methods in identifying both textured and less-textured objects.

Conclusions:

The SPCNN-RBOR method provides a robust and effective solution for object recognition in challenging real-world scenarios.
The integration of SPCNN with region-based matching overcomes limitations of traditional feature-based approaches.
This method offers significant improvements for identifying objects across a wide range of textures and environmental conditions.