Related Experiment Video
Updated: Jul 2, 2026

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging
Published on: July 11, 2025
A spatially variant white-patch and gray-world method for color image enhancement driven by local contrast
Edoardo Provenzi1, Carlo Gatta, Massimo Fierro
1Dipartimento di Tecnologies dell'Informazione, Università degli Studi di Milano, Crema, Italy. provenzi@dti.unimi.it
A novel color correction model, RACE, combines Random Spray Retinex (RSR) and Automatic Color Equalization (ACE) for improved performance. A new regulation mechanism addresses common drawbacks in differential color correction models.
Area of Science:
- Computer Vision
- Image Processing
- Color Science
Background:
- Perceptually inspired color correction models like Retinex are crucial for image reproduction and feature recognition.
- Existing models, including white-patch (WP) and gray-world (GW) algorithms, have distinct characteristics and limitations.
- Differential, spatially-variant, and non-linear approaches are common in these color correction techniques.
Purpose of the Study:
- To develop a more robust and higher-performing color correction model by integrating WP and GW algorithms.
- To address the common drawback of uniform image area corruption found in differential color correction models.
- To introduce a generalizable regulation mechanism applicable to various perceptually inspired color correction algorithms.
Main Methods:
- A unified spatially-variant approach was identified for Random Spray Retinex (RSR) and Automatic Color Equalization (ACE).
- The distinct non-linear and differential mechanisms of RSR and ACE were mathematically fused using spray techniques and local averaging.
- A local and global contrast-based, image-driven regulation mechanism was devised to overcome image corruption in uniform areas.
Main Results:
- The combined model, RACE (Random Spray Retinex and Automatic Color Equalization), demonstrated enhanced robustness and performance compared to individual algorithms.
- A significant drawback of differential models, the corruption of uniform image areas, was identified and addressed.
- The proposed regulation mechanism proved effective in mitigating artifacts and improving overall color correction quality.
Conclusions:
- The RACE model offers a superior approach to color correction by synergistically combining WP and GW algorithms.
- The developed regulation mechanism provides a general solution for improving perceptually inspired color correction techniques.
- This research advances the field of image processing by offering a more robust and artifact-free color correction solution.
Related Concept Videos
Color Vision
Gradient Fields
Differential Staining Technique
Perceptual Constancy
Size constancy is the recognition that an object remains the same size, even when its image on the retina changes. For instance, a bus is perceived to be large enough to carry people, even if it looks tiny from...
Depth Perception and Spatial Vision
Special Staining Techniques