Perceptually Consistent Color-to-Gray Image Conversion

TL;DR

This paper introduces a perceptually consistent color-to-gray conversion algorithm that preserves brightness and contrast, validated through datasets and user studies, improving over existing methods.

Contribution

The paper presents a novel graph-based optimization framework for color-to-gray conversion that explicitly models perceptual brightness and contrast, with an $ ext{l}_1$-norm solution to enhance perceptual fidelity.

Findings

Improved performance metrics over existing C2G algorithms.

Validated perceptual quality through user studies.

Effective handling of diverse image scenarios in NeoColor dataset.

Abstract

In this paper, we propose a color to grayscale image conversion algorithm (C2G) that aims to preserve the perceptual properties of the color image as much as possible. To this end, we propose measures for two perceptual properties based on contemporary research in vision science: brightness and multi-scale contrast. The brightness measurement is based on the idea that the brightness of a grayscale image will affect the perception of the probability of color information. The color contrast measurement is based on the idea that the contrast of a given pixel to its surroundings can be measured as a linear combination of color contrast at different scales. Based on these measures we propose a graph based optimization framework to balance the brightness and contrast measurements. To solve the optimization, an $\ell_1$-norm based method is provided which converts color discontinuities to brightness discontinuities. To validate our methods, we evaluate against the existing \cadik and Color250 datasets, and against NeoColor, a new dataset that improves over existing C2G datasets. NeoColor contains around 300 images from typical C2G scenarios, including: commercial photograph, printing, books, magazines, masterpiece artworks and computer designed graphics. We show improvements in metrics of performance, and further through a user study, we validate the performance of both the algorithm and the metric.