Color Image Enhancement Using the lrgb Coordinates in the Context of Support Fuzzification

TL;DR

This paper proposes a novel color image enhancement method using lrgb coordinates and fuzzy partitions to improve brightness and saturation adjustments, reducing boundary artifacts and enhancing image quality.

Contribution

It introduces a new affine transform approach in lrgb space combined with fuzzy partitioning for improved color image enhancement.

Findings

Fuzzy partitioning reduces boundary artifacts in image enhancement.

The method allows separated control of luminosity and saturation.

Enhanced images show better quality compared to classical methods.

Abstract

Image enhancement is an important stage in the image-processing domain. The most known image enhancement method is the histogram equalization. This method is an automated one, and realizes a simultaneous modification for brightness and contrast in the case of monochrome images and for brightness, contrast, saturation and hue in the case of color images. Simple and efficient methods can be obtained if affine transforms within logarithmic models are used. A very important thing in the affine transform determination for color images is the coordinate system that is used for color space representation. Thus, the using of the RGB coordinates leads to a simultaneous modification of luminosity and saturation. In this paper using the lrgb perceptual coordinates one can define affine transforms, which allow a separated modification of luminosity l and saturation s (saturation being calculated with the component rgb in the chromatic plane). Better results can be obtained if partitions are defined on the image support and then the pixels are separately processed in each window belonging to the defined partition. Classical partitions frequently lead to the appearance of some discontinuities at the boundaries between these windows. In order to avoid all these drawbacks the classical partitions may be replaced by fuzzy partitions. Their elements will be fuzzy windows and in each of them there will be defined an affine transform induced by parameters using the fuzzy mean, fuzzy variance and fuzzy saturation computed for the pixels that belong to the analyzed window. The final image is obtained by summing up in a weight way the images of every fuzzy window.