Low-light image restoration using bright channel prior-based variational Retinex model

Seonhee Park,Joonki Paik,Seungyong Ko,Byeongho Moon,Soohwan Yu

doi:10.1186/s13640-017-0192-3

Seonhee Park, Joonki Paik + Show 3 more

Open Access

https://doi.org/10.1186/s13640-017-0192-3

Copy DOI

Abstract

This paper presents a low-light image restoration method based on the variational Retinex model using the bright channel prior (BCP) and total-variation minimization. The proposed method first estimates the bright channel to control the amount of brightness enhancement. Next, the variational Retinex-based energy function is iteratively minimized to estimate the improved illumination and reflectance using the BCP. Contrast of the estimated illumination is enhanced using the gamma correction and histogram equalization to reduce a color distortion and noise amplification. Experimental results show that the proposed method can provide the better restored result than the existing methods without unnatural artifacts such as noise amplification and halo effects near edges.

Highlights

1 Introduction Various imaging systems that consist of an optical system and imaging sensor have been widely used in various industrial and consumer application fields such as advanced driver assistance systems (ADAS), surveillance systems, robot vision, and medical imaging [1]
We present the low-light image restoration method using the variational optimization-based Retinex model and bright channel prior (BCP)
We present a variational retinex model using l1- and l2-norm minimization to enhance a lowlight image

Summary

Introduction

Various imaging systems that consist of an optical system and imaging sensor have been widely used in various industrial and consumer application fields such as advanced driver assistance systems (ADAS), surveillance systems, robot vision, and medical imaging [1]. The low-light artifacts make the post-processing step difficult such as object recognition, detection, and tracking To solve this problem, various image brightness enhancement methods have been proposed in the literature. The resulting image shows the halo effect near the edges To solve this problem, the state-of-the-art Retinex methods incorporate with the variational optimization method using l1- and l2-norm minimization [15, 16]. Li et al proposed a variational Retinex method using the constraint term that minimizes the combined reflectance component and the image gradient to reduce the halo effect [17]. Fu et al proposed the bright channel prior (BCP) to reduce the halo effect and color distortion using l2-norm minimization on the illumination and reflectance components [19]. We present the low-light image restoration method using the variational optimization-based Retinex model and BCP.

Theoretical background

Low-light image restoration method using the bright channel prior

Optimal reflectance and illumination components estimation

Objective performance evaluation using simulated low-light images

Conclusions