Computer Science ›› 2022, Vol. 49 ›› Issue (6): 199-209.doi: 10.11896/jsjkx.210400092

• Computer Graphics & Multimedia • Previous Articles     Next Articles

Low-light Image Enhancement Based on Retinex Theory by Convolutional Neural Network

ZHAO Zheng-peng1, LI Jun-gang1, PU Yuan-yuan1,2   

  1. 1 School of Information Science and Engineering,Yunnan University,Kunming 650504,China
    2 Key Laboratory of Internet of Things Technology and Application in Colleges and Universities,Kunming 650504,China
  • Received:2021-04-09 Revised:2021-09-10 Online:2022-06-15 Published:2022-06-08
  • About author:ZHAO Zheng-peng,born in 1973,asso-ciate professor.His main research in-terests include communication and information systems,voice signal proces-sing and image processing.
    LI Jun-gang,born in 1995,postgra-duate.His main research interests include image enhancement and so on.
  • Supported by:
    National Natural Science Foundation of China(61271361,61761046,U1802271),Key Program of the Applied Basic Research Programs of Yunnan(202001BB050043) and Scientific Research Project of Yunnan Provincial Department of Education(2019Y0004).

Abstract: In the course of decomposing and enhancing the low-light images with Retinex model,it needs to manually adjust the parameters continuously to reach the optimal solution,which will reduce the efficiency of the entire process.In addition,existing low-light image enhancement methods based on Retinex fail to take both reflectance and illumination into account when perfor-ming image enhancement,and there are problems such as too much noise in the reflectance of low-light image,low brightness and not enough prominent details in the illumination.Aiming to solve these problems,a data-driven deep network is proposed to learn the decomposition and the enhancement of the low-light images,and the model parameters are learned through the end-to-end network training.The network firstly decomposes the low-light images into the reflectance and the illumination.Aiming at the problem of high noise in the reflectance,an improved denoising convolutional neural network model NDnCNN is used for denoising,and aiming at the problems of low brightness and not enough prominent details in the illumination,we introduce the convolutional block attention model CBAM to enhance the details and guide the network to modify the illumination.Finally,the denoised reflectance and the modified illumination are used for image reconstruction.Experimental results show that the enhanced low-light image is more photo-realistic with increased brightness,prominent details,rich information and low image distortion.

Key words: Convolutional block attention model, Convolutional neural network, Improved DnCNN model, Low-light image enhancement, Retinex theory

CLC Number: 

  • TP391
[1] REFAEL C.Digital image processing(2 Edition)[M].Translated by RUAN Q Q.Beijing:Publishing House of Electronics Industry,2003.
[2] MOU Q,WEI Y Y,LI J,et al.Research on Improved Retinex Low Illumination Image Enhancement Algorithm[J].Journal of Harbin Engineering University,2018,39(12):2001-2010.
[3] LI Q Z,LIU Q.Adaptive enhancement algorithm for low illumination image based on wavelet transform[J].Chinese Journal of Lasers,2015,42(2):280-286.
[4] ZHANG Y J.Image Engineering Volume-Image Processing and Analysis[M].Beijing:Tsinghua University Press,2006.
[5] JAIN A.Fundamentals of Digital Image Processing[M].Englewood Cliffs,NJ:Prentice Hall,1989.
[6] IBRAHIM H,KONG N S P.Brightness Preserving DynamicHistogram Equalization for Image Contrast Enhancement[J].IEEE Transactions on Consumer Electronics,2007,53(4):1752-1758.
[7] CHAO W,YE Z.Brightness preserving histogram equalization with maximum entropy:a variational perspective[J].IEEE Transactions on Consumer Electronics,2005,51(4):1326-1334.
[8] CHEN S D,RAMLI A R.Minimum mean brightness error Bi-histogram equalization in contrast enhancement[J].IEEE Transactions on Consumer Electronics,2003,49(4):1310.
[9] YUE H,YANG J,SUN X,et al.Contrast enhancement based on intrinsic image decomposition[J].IEEE Transactions on Image Processing,2017,26(8):3981-3994.
[10] LAND E H,MCCANN J J.Lightness and retinextheory[J].Journal of the Optical Society of America,1971,61(1):1-11.
[11] JOBSON D J,RAHMAN Z U,WOODELL G A.Properties and Performance of a Center/Surround Retinex[J].IEEE Transactions on Image Processing,1997,6(3):451-462.
[12] RAHMAN Z U,JOBSON D J,WOODELL G W.Multiscale retinex for color rendition and dynamic range compression[J].Proc Spie,1996,2847:183-191.
[13] COOPER T J,BAQAI F A.Analysis and extensions of theFrankle-McCann Retinex algorithm[J].Journal of Electronic Imaging,2004,13(1):85-92.
[14] LORE K G,AKINTAYO A,SARKAR S.LLNet:A DeepAutoencoder Approach to Natural Low-light Image Enhancement[J].Pattern Recognition,2017,61:650-662.
[15] MA H Q,MA S P,XU Y L,et al.Low-light image enhancement based on deep convolutional neural network[J].Acta Optica Sinica,2019,39(2):91-100.
[16] SHEN L,YUE Z,FENG F,et al.MSR-net:Low-light Image Enhancement Using Deep Convolutional Network[J].arXiv:1711.02488.
[17] WEI C,WANG W,YANG W,et al.Deep retinex decomposition for low-light enhancement[C]//British Machine Vision Confe-rence(BMVC).2018.
[18] ZHANG Y,ZHANG J,GUO X,et al.Kindling the Darkness:A Practical Low-Light Image Enhancer[C]//ACM Multimedia.2019:1632-1640.
[19] WU R Y,WANG D X,YUAN H C,et al.Low illuminationimage enhancement based on multi-branch fully convolutional neural network[J].Progress in Laser and Optoelectronics,2020,57(14):197-207.
[20] LI J H,WNAG K.A Low-light Image Enhancement Method Based on Convolutional Neural Network[J].Journal of Jiangxi University of Science and Technology,2020,41(5):73-79.
[21] CHAN S H,KHOSHABEH R,GIBSON K B,et al.An Augmented Lagrangian Method for Total Variation Video Restoration[J].IEEE Transactions on Image Processing,2011,20(11):3097-3111.
[22] ZHANG K,ZUO W,CHEN Y,et al.Beyond a Gaussian Denoi-ser:Residual Learning of Deep CNN for Image Denoising[J].IEEE Transactions on Image Processing,2016,26(7):3142-3155.
[23] WOO S,PARK J,LEE J Y,et al.Cbam:Convolutionalblock attention module[C]//Proceedings of the European Conference on Computer Vision(ECCV).2018:3-19.
[24] MITTAL A,SOUNDARARAJAN R.Making a ‘CompletelyBlind’ Image Quality Analyzer[J].IEEE Signal Processing Letters,2013,20(3):209-212.
[25] DANG-NGUYEN D T,PASQUINI C,CONOTTER V,et al.RAISE:a raw images dataset for digital image forensics[C]//ACM Multimedia Systems Conference.ACM,2015:219-224.
[26] WANG S H,ZHENG J,HUH M,et al.Naturalness preserved enhancement algorithm for non-uniform illumination images[J].IEEE Transactions on Image Processing,2013,22(9):3538-3548.
[27] GUO X J,LI Y,LING H B.Lime:Low-light image enhancement via illumination map estimation[J].IEEE Transactions on Image Processing,2017,26(2):982-993.
[28] LEE C,LEE C,KIM C S.Contrast enhancement based on la-yered difference representation of 2D histograms[J].IEEE Transactions on Image Processing,2013,22(12):5372-5384.
[29] ROTH S,BLACK M J.Fields of experts[J].International Journal of Computer Vision,2009,82(2):205-229.
[30] LOH Y P,CHAN C S.Getting to know low-light images with the Exclusively Dark dataset[J].Computer Vision and Image Understanding,2019,178:30-42.
[31] MA K,ZENG K,WANG Z.Perceptual Quality Assessment for Multi-Exposure Image Fusion[J].IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society,2015,24(11):3345-3356.
[32] LV F F,LU F,WU J H,et al.MBLLEN:Low-light Image/Video Enhancement Using CNNs[C]//British Machine Vision Conference(BMVC).2018.
[33] FU X,ZENG D,HUANG Y,et al.A Weighted VariationalModel for Simultaneous Reflectance and Illumination Estimation[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2016:2782-2790.
[34] YING Z,LI G,GAO W.A bio-inspired multi-exposure fusion framework for low-light image enhancement[J].arXiv:1711.00591,2017.
[35] LI M,LIU J,YANG W,et al.Structure-Revealing Low-LightImage Enhancement Via Robust Retinex Model[J].IEEE Transactions on Image Processing,2018,27(6):2828-2841.
[36] Al-AMEEN Z.Nighttime image enhancement using a new illumination boost algorithm[J].Image Processing,IET,2019,13(8):1314-1320.
[37] DAI Q,PU Y F,RAHMAN Z,et al.Fractional-Order FusionModel for Low-Light Image Enhancement[J].Symmetry,2019,11(4):574-591.
[38] LU K,ZHANG L.TBEFN:A Two-Branch Exposure-Fusion Network for Low-Light Image Enhancement[J].IEEE Transactions on Multimedia,2021,23:4093-4105.
[39] HAO S,HAN X,GUO Y,et al.Low-Light Image Enhancement with Semi-Decoupled Decomposition[J].IEEE Transactions on Multimedia,2020,22(12):3025-3038.
[1] ZHOU Le-yuan, ZHANG Jian-hua, YUAN Tian-tian, CHEN Sheng-yong. Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion [J]. Computer Science, 2022, 49(9): 155-161.
[2] CHEN Yong-quan, JIANG Ying. Analysis Method of APP User Behavior Based on Convolutional Neural Network [J]. Computer Science, 2022, 49(8): 78-85.
[3] ZHU Cheng-zhang, HUANG Jia-er, XIAO Ya-long, WANG Han, ZOU Bei-ji. Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism [J]. Computer Science, 2022, 49(8): 113-119.
[4] DAI Zhao-xia, LI Jin-xin, ZHANG Xiang-dong, XU Xu, MEI Lin, ZHANG Liang. Super-resolution Reconstruction of MRI Based on DNGAN [J]. Computer Science, 2022, 49(7): 113-119.
[5] LIU Yue-hong, NIU Shao-hua, SHEN Xian-hao. Virtual Reality Video Intraframe Prediction Coding Based on Convolutional Neural Network [J]. Computer Science, 2022, 49(7): 127-131.
[6] XU Ming-ke, ZHANG Fan. Head Fusion:A Method to Improve Accuracy and Robustness of Speech Emotion Recognition [J]. Computer Science, 2022, 49(7): 132-141.
[7] WU Zi-bin, YAN Qiao. Projected Gradient Descent Algorithm with Momentum [J]. Computer Science, 2022, 49(6A): 178-183.
[8] YANG Yue, FENG Tao, LIANG Hong, YANG Yang. Image Arbitrary Style Transfer via Criss-cross Attention [J]. Computer Science, 2022, 49(6A): 345-352.
[9] YANG Jian-nan, ZHANG Fan. Classification Method for Small Crops Combining Dual Attention Mechanisms and Hierarchical Network Structure [J]. Computer Science, 2022, 49(6A): 353-357.
[10] ZHANG Jia-hao, LIU Feng, QI Jia-yin. Lightweight Micro-expression Recognition Architecture Based on Bottleneck Transformer [J]. Computer Science, 2022, 49(6A): 370-377.
[11] WANG Jian-ming, CHEN Xiang-yu, YANG Zi-zhong, SHI Chen-yang, ZHANG Yu-hang, QIAN Zheng-kun. Influence of Different Data Augmentation Methods on Model Recognition Accuracy [J]. Computer Science, 2022, 49(6A): 418-423.
[12] SUN Jie-qi, LI Ya-feng, ZHANG Wen-bo, LIU Peng-hui. Dual-field Feature Fusion Deep Convolutional Neural Network Based on Discrete Wavelet Transformation [J]. Computer Science, 2022, 49(6A): 434-440.
[13] HU Fu-yuan, WAN Xin-jun, SHEN Ming-fei, XU Jiang-lang, YAO Rui, TAO Zhong-ben. Survey Progress on Image Instance Segmentation Methods of Deep Convolutional Neural Network [J]. Computer Science, 2022, 49(5): 10-24.
[14] XU Hua-chi, SHI Dian-xi, CUI Yu-ning, JING Luo-xi, LIU Cong. Time Information Integration Network for Event Cameras [J]. Computer Science, 2022, 49(5): 43-49.
[15] LIU Lin-yun, CHEN Kai-yan, LI Xiong-wei, ZHANG Yang, XIE Fang-fang. Overview of Side Channel Analysis Based on Convolutional Neural Network [J]. Computer Science, 2022, 49(5): 296-302.
Full text



No Suggested Reading articles found!