A night low‐illumination image enhancement model based on small probability area filtering and lossless mapping enhancement

Abstract

A novel night-time image enhancement approach was proposed in this paper to address the problems of low contrast and poor details of low-illumination images captured at night. To begin with, the luminance component V was extracted that was irrelevant to the colour information of the image upon converting the image to the HSV space from the RGB space. Then, by converting the luminance component V of the image into the probability space, the image was divided into a small-probability grey-scale area and a normal area based on the theory of probability. Moreover, pixels were transferred from the small probability area to the normal area of the image according to the nearest attribution principle that was established. Lastly, the contrast enhancement of the image was realized thanks to lossless mapping functions without losing the number of grey levels of the image. As can be observed from experimental results, the proposed method is superior to the most advanced algorithm in visual quality and quantitative measurement.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Low‐light image enhancement via span correction function and discrete mapping model

“…Currently, the enhancement methods of low-light images mainly include four categories: Grey Mapping-based, Retinex-based, HE-based, and Deep Learning-based [16].…”

Image Enhancement and Brightness Equalization Algorithms in Low Illumination Environment Based on Multiple Frame Sequences

“…Although this method has been widely studied, it still lacks persuasiveness. At present, in image processing, the processing methods for LIIs pay more attention to the enhancement, either ignoring image denoising or using it as post-processing, resulting in poor IE and damaging the details in the image [15].…”

“…In equation ( 13), F Integ is the one value integral of F. Then, based on the mean F of F, the image sensitivity parameter T is expressed as equation (14). After determining the image sensitivity parameter T , the image is re integrated, and the expression for the binary image is equation (15).…”

“…By comparing the brightness fluctuation with the original image, the effectiveness of the algorithm was evaluated. The performance analysis of the WASOBI blind source noise reduction algorithm uses the traditional support vector machine (SVM) SVM and Convolutional neural network (CNN) CNN, as well as the latest image processing algorithms in literature [14] and literature [15] as comparison algorithms. The algorithm proposed in reference [14] is a low light image enhancement method based on Retinex decomposition, mainly using gamma correction and lightweight networks to process the brightness of the image.…”

“…The algorithm proposed in reference [14] is a low light image enhancement method based on Retinex decomposition, mainly using gamma correction and lightweight networks to process the brightness of the image. Reference [15] is an image brightness enhancement algorithm optimized using probability theory, which divides the grayscale levels of the image through probability analysis to achieve brightness balance. The performance analysis of Peel's growth curve uses linear growth curve as a comparison method.…”