Abstract

Modeling the local color spatial distribution is a crucial step for the algorithms of the Milano Retinex family. Here we present GREAT, a novel, noise-free Milano Retinex implementation based on an image-aware spatial color sampling. For each channel of a color input image, GREAT computes a 2D set of edges whose magnitude exceeds a pre-defined threshold. Then GREAT re-scales the channel intensity of each image pixel, called target, by the average of the intensities of the selected edges weighted by a function of their positions, gradient magnitudes, and intensities relative to the target. In this way, GREAT enhances the input image, adjusting its brightness, contrast and dynamic range. The use of the edges as pixels relevant to color filtering is justified by the importance that edges play in human color sensation. The name GREAT comes from the expression “Gradient RElevAnce for ReTinex,” which refers to the threshold-based definition of a gradient relevance map for edge selection and thus for image color filtering.

© 2017 Optical Society of America

Energy-driven path search for Termite Retinex

Michela Lecca, Alessandro Rizzi, and Gabriele Gianini
J. Opt. Soc. Am. A 33(1) 31-39 (2016)

Generalized equation for real-world image enhancement by Milano Retinex family

Michela Lecca
J. Opt. Soc. Am. A 37(5) 849-858 (2020)

SuPeR: Milano Retinex implementation exploiting a regular image grid

Michela Lecca and Stefano Messelodi
J. Opt. Soc. Am. A 36(8) 1423-1432 (2019)

QBRIX: a quantile-based approach to retinex

Gabriele Gianini, Andrea Manenti, and Alessandro Rizzi
J. Opt. Soc. Am. A 31(12) 2663-2673 (2014)

A population-based approach to point-sampling spatial color algorithms

Gabriele Gianini, Michela Lecca, and Alessandro Rizzi
J. Opt. Soc. Am. A 33(12) 2396-2413 (2016)