A low-light image enhancement method based on HSV space

Abstract

ABSTRACTTo enhance the visual performance of low-illumination images, many low-illumination images are analyzed. Based on this, a low-light image enhancement method based on HSV space and semi-implicit ROF model is proposed. First, the low-illumination image is decomposed into HSV space for saturation denoising and brightness enhancement. Then, the Bayesian rules are applied to fuse the saturation and value. The three components in HSV space are converted to the RGB space and obtain a rough enhanced image. Finally, the semi-implicit ROF model is introduced to denoise the global noise and obtain the enhanced image. Such a comprehensive method can improve the low illumination image more clearly. The experimental results show that the algorithm has a PSNR score of 26.48, 6.29, 0.8947, and 28.4124, and the PSNR score is the highest in the comparison algorithm. The experiments on the Low-Light image data set also show that the proposed method can effectively improve the visibility of low-light images, and can provide a simple and effective method for low-light image enhancement.KEYWORDS: Image enhancementDeep learningHSV color spaceBayesian ruleROFGaussian noiseStructure SimilarityPeak Signal Noise Ratio Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationNotes on contributorsLibing ZhouLibing Zhou received master's degree from Hefei University of Technology, Hefei, China. Now he works at Tiandi(Changzhou) Automation Co., Ltd. His current research interests include mine electromechanical system intelligent, intelligent detection and control.Xiaojing ChenXiaojing Chen is an associate research fellow. Now he works at Tiandi(Changzhou) Automation Co., Ltd. His current research interests include coal mine industrial control, Internet of Things and intelligent technology.Baisong YeBaisong Ye received PhD degree from the University of Science and Technology of China, Hefei, China, in 2013. Now he works at Tiandi(Changzhou) Automation Co., Ltd. His current research interests includecoal mine photoelectric detection system and intelligent application technology.Xueli JiangXueli Jiang received PhD degreefrom the University of Science and Technology of China, Hefei,China, in 2021. Now he works at Tiandi(Changzhou) Automation Co., Ltd. His current research focuses on motor control.Sheng ZouZhengqian Yu received master's degree from the Stevens Institute of Technology, New Jersey,USA, in 2020. Now he works at Tiandi(Changzhou) Automation Co., Ltd. His current research interests include positioning, object detection and obstacle perception.Liang JiJianjian Wei received master's degree from Xi'an University of Science and Technology, Xi'an,China, in 2022. Now he works at Tiandi(Changzhou) Automation Co., Ltd. His current research interests include positioning, object detection.Zhengqian YuSheng Zou received master's degree from University of South China, Hengyang,China, in 2019. Now he works at Tiandi(Changzhou) Automation Co., Ltd. His current research interests include visual image processing in coal mine.Jianjian WeiLiang Ji received master's degree from China University of Mining and Technology, Xuzhou,China, in 2019. Now he works at Tiandi(Changzhou) Automation Co., Ltd. His current research interests include mine intelligence, artificial intelligence and deep learning.Yexin ZhaoYexin Zhao received master's degree from Chang'an University, Xi'an, China, in 2020. Now he works at Tiandi(Changzhou) Automation Co., Ltd. His current research interests include decision control for autonomous driving.Tianyu WangTianyu Wang received master's degree from Jiangsu University, Zhenjiang, China, in 2019. Now he works at Tiandi(Changzhou) Automation Co., Ltd. His current research interests include control, automation and structural design.