Abstract
Images taken at night, under cloudy conditions, etc., are degraded and of poor quality, which can cause problems such as low brightness, excessive noise, and loss of information. In recent years, deep learning-based methods have led to a significant breakthrough in the challenging task of processing the enhancement of low-light images. We propose a new attention-based network incorporating Retinex theory for the enhancement of low-light images. First, the method in this paper requires pairs of low-/normal-light images for training, and the respective illumination and reflectance maps are decomposed by the first part of the designed network according to the commonality of both. Secondly, an attention mechanism module is inserted in the convolutional layer in the second part of the network, to adaptively adjust the luminance information of the illumination and to preserve the consistency of the image structure. Finally, the new illumination map estimated in the second part is combined with the previous reflectance map to obtain the final enhanced image. The experimental results show that the method achieves better results both quantitatively and qualitatively, with obvious luminance enhancement, less noise, better color reproduction, clearer texture information, and overall superiority compared to existing advanced methods.
Similar content being viewed by others
References
Al-Nawashi M, Al-Hazaimeh OM, Saraee M (2017) A novel framework for intelligent surveillance system based on abnormal human activity detection in academic environments. Neural Comput Applic 28(1):565–572
Alsmirat MA, Al-Alem F, Al-Ayyoub M, Jararweh Y, Gupta B (2019) Impact of digital fingerprint image quality on the fingerprint recognition accuracy. Multimed Tools Appl 78(3):3649–3688
Atawneh S, Almomani A, Al Bazar H, Sumari P, Gupta B (2017) Secure and imperceptible digital image steganographic algorithm based on diamond encoding in DWT domain. Multimed Tools Appl 76(18):18451–18472
Banerjee S, Chaudhuri S (2020) Nighttime image-dehazing: a review and quantitative benchmarking. Arch Comput Methods Eng:1–33
Cai B, Xu X, Guo K, Jia K, Hu B, Tao D (2017) A joint intrinsic-extrinsic prior model for retinex. In: IEEE International conference on computer vision (ICCV), pp 4020–4029. IEEE computer society
Du J, He Z, Wang L, Gholipour A, Zhou Z, Chen D, Jia Y (2020) Super-resolution reconstruction of single anisotropic 3D MR images using residual convolutional neural network. Neurocomputing 392:209–220
Esposito C, Ficco M, Gupta BB (2021) Blockchain-based authentication and authorization for smart city applications. Inf Process Manage 58(2):102468
Fu G, Duan L, Xiao C (2019) A hybrid l2-LP variational model for single Low-Light image enhancement with bright channel prior. In: 2019 IEEE International conference on image processing (ICIP). pp 1925–1929
Fu X, Zeng D, Huang Y, Zhang XS, Ding X (2016) A weighted variational model for simultaneous reflectance and illumination estimation. In: 2016 IEEE Conference on computer vision and pattern recognition, CVPR, pp 2782–2790. IEEE Computer Society
Gregor K, Danihelka I, Graves A, Rezende DJ, Wierstra D (2015) DRAW: A recurrent neural network for image generation. In: Proceedings of the 32nd international conference on machine learning, ICML, vol 37. pp 1462–1471. JMLR.org
Guo C, Li C, Guo J, Loy CC, Hou J, Kwong S, Cong R (2020) Zero-reference Deep curve estimation for Low-Light image enhancement. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 1780–1789
Guo C, Li C, Guo J, Loy CC, Hou J, Kwong S, Cong R (2020) Zero-Reference Deep curve estimation for Low-Light image enhancement. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 1780–1789
Guo X, Li Y, Ling H (2017) LIME: Low-Light image enhancement via illumination map estimation. IEEE Transon Image Process 26(2):982–993
Huang O, Long W, Bottenus N, Lerendegui M, Trahey GE, Farsiu S, Palmeri ML (2020) Mimicknet, mimicking clinical image post-processing under black-box constraints. IEEE Trans Med Imaging 39(6):2277–2286
Jiang Y, Gong X, Liu D, Cheng Y, Fang C, Shen X, Yang J, Zhou P, Wang Z (2021) EnlightenGAN: deep light enhancement without paired supervision. IEEE Trans Image Process 30:2340–2349
Land EH, McCann JJ (1971) Lightness and retinex theory. J Opt Soc Am 61(1):1–11
Lee H, Sohn K, Min D (2020) Unsupervised low-light image enhancement using bright channel prior. IEEE Signal Process Lett 27:251–255
Li D, Deng L, Gupta BB, Wang H, Choi C (2019) A novel CNN based security guaranteed image watermarking generation scenario for smart city applications. Inf Sci 479:432–447
Li J, Feng X, Fan H (2020) Saliency-based image correction for colorblind patients. Comput Vis Med 6(2):169–189
Li J, Feng X, Hua Z (2021) Low-Light image enhancement via progressive-recursive network. IEEE Trans Circuits Syst Video Technol 31 (11):4227–4240
Li C, Guo J, Porikli F, Pang Y (2018) Lightennet: a convolutional neural network for weakly illuminated image enhancement. Pattern Recogn Lett 104:15–22
Li J, Li G, Fan H (2018) Image dehazing using residual-based deep CNN. IEEE Access 6:26831–26842
Liming T, Honglu Z, Chuanjiang H, Zhuang F (2019) Non-convex and non-smooth variational decomposition for image restoration. Appl Math Model 69:355–377
Liu D, Wen B, Jiao J, Liu X, Wang Z, Huang TS (2020) Connecting image denoising and high-level vision tasks via deep learning. IEEE Trans Image Process 29:3695–3706
Lore KG, Akintayo A, Sarkar S (2017) LLNEt: A deep autoencoder approach to natural low-light image enhancement. Pattern Recogn 61:650–662
Mnih V, Heess N, Graves A, Kavukcuoglu K (2014) Recurrent models of visual attention. In: Advances in neural information processing systems 27: Annual conference on neural information processing systems, pp 2204–2212
Opschoor JAA, Petersen PC, Schwab C (2020) Deep reLU networks and high-order finite element methods. Anal Appl 18(5):715–770
Pan Y, He F, Yu H (2019) A novel enhanced collaborative autoencoder with knowledge distillation for top-N recommender systems. Neurocomputing 332:137–148
Pan Y, He F, Yu H (2020) Learning social representations with deep autoencoder for recommender system. World Wide Web 23(4):2259–2279
Pan Y, He F, Yu H (2020) A correlative denoising autoencoder to model social influence for top-N recommender system. Front Comput Sci 14(3):143301
Park S, Yu S, Kim M, Park K, Paik J (2018) Dual autoencoder network for retinex-based low-light image enhancement. IEEE Access 6:22084–22093
Park S, Yu S, Moon B, Ko S, Paik J (2017) Low-light image enhancement using variational optimization-based retinex model. IEEE Trans Consum Electron 63(2):178–184
Pizer SM, Amburn EP, Austin JD, Cromartie R, Geselowitz A, Greer T, Romeny BTH, Zimmerman JB (1987) Adaptive histogram equalization and its variations. Comput Vis Graph Lmage Process 39(3):355–368
Popel M, Tomkova M, Tomek J, Kaiser L, Uszkoreit J, Bojar O, Zabokrtsky Z (2020) Transforming machine translation: a deep learning system reaches news translation quality comparable to human professionals. Nature communications 11(1):1–15
Rasti B, Ghamisi P (2020) Remote sensing image classification using subspace sensor fusion. Inf Fusion 64:121–130
Ren X, Li M, Cheng W, Liu J (2018) Joint enhancement and denoising method via sequential decomposition. In: IEEE International symposium on circuits and systems, ISCAS, pp 1–5, IEEE
Ren WQ, Liu SF, Ma L, Xu QQ, Xu XY, Cao XC, Du JP, Yang MH (2019) Low-light image enhancement via a deep hybrid network. IEEE Trans Image Process 28(9):4364–4375
Singh P, Mukundan R, De Ryke R (2019) Feature enhancement in medical ultrasound videos using contrast-limited adaptive histogram equalization. J Digit Imaging 33(1):273–285
Talaulikar Abhijeet S, Sanathanan S, Modi CN (2019) An enhanced approach for detecting helmet on motorcyclists using image processing and machine learning techniques, pp 109–119, Advanced Computing and Communication Technologies
Tian C, Fei L, Zheng W, Xu Y, Zuo W, Lin CW (2020) Deep learning on image denoising: an overview. Neural Netw 131:251–275
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems 30: Annual conference on neural information processing systems, pp 5998–6008
Wang H, Li Z, Li Y, Gupta BB, Choi C (2020) Visual saliency guided complex image retrieval. Pattern Recogn Lett 130(SI):64–72
Wang R, Zhang Q, Fu CW, Shen X, Zheng WS, Jia J (2019) Underexposed photo enhancement using deep illumination estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6849–6857 Computer Vision Foundation / IEEE
Wei C, Wang W, Yang W, Liu J (2018)
Xu J, Hou Y, Ren D, Liu L, Zhu F, Yu M, Shao L (2020) STAR: A structure and texture aware retinex model. IEEE Trans Image Process 29:5022–5037
Yu C, Li J, Li X, Ren X, Gupta BB (2018) Four-image encryption scheme based on quaternion fresnel transform, chaos and computer generated hologram. Multimed Tools Appl 77(4):4585–4608
Zhang Y, Di X, Zhang B, Wang C (2020) Self-supervised image enhancement network: Training with Low Light images only, arXiv:2002
Zhang H, Goodfellow IJ, Metaxas DN, Odena A (2019) Self-attention generative adversarial networks. In: Proceedings of the 36th international conference on machine learning, ICML, Proceedings of Machine Learning Research, vol 97. pp 7354–7363, PMLR
Zhang S, He F (2020) DRCDN: Learning deep residual convolutional dehazing networks. Vis Comput 36(9):1797–1808
Zhang T, Li J, Fan H (2022) Progressive edge-sensing dynamic scene deblurring. Comput. Vis. Media 8(3):495–508
Zhang Y, Zhang J, Guo X (2019) Kindling the darkness: a practical low-light image enhancer. In: Proceedings of the 27th ACM international conference on multimedia, pp 1632–1640, ACM
Zimmerman JB, Pizer SM, Staab EV, Perry JR, McCartney W, Brenton BC (1988) An evaluation of the effectiveness of adaptive histogram equalization for contrast enhancement. IEEE Trans Med Imaging 7(4):304–312
Acknowledgements
The authors acknowledge the National Natural Science Foundation of China (Grant nos. 61772319, 62002200, 61972235, and 12001327), and Shandong Natural Science Foundation of China (Grant no. ZR2020QF012 and ZR2021MF068).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interests
All authors declare that there are no conflicts of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Chen, X., Li, J. & Hua, Z. Retinex low-light image enhancement network based on attention mechanism. Multimed Tools Appl 82, 4235–4255 (2023). https://doi.org/10.1007/s11042-022-13411-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-13411-z