Abstract
In low-light scenes, due to the limitations of ambient light and camera hardware equipment, the images captured by imaging devices often have low brightness, low contrast, high noise and loss of detail, which can cause great interference in face recognition, video surveillance and other application scenarios. Accordingly, a dark image enhancement method based on multi-scale features and dilated residual networks is proposed to solve the above problem. The input to the network is the V channel of the image HSV color space. The network uses a multiscale feature extractor to extract shallow features from the image, then a new dilated residual network constructed in this paper is used to extract deep features from the image, and finally the enhanced V-component is obtained by a single-channel convolutional layer. The final enhanced low-illumination image is obtained by component fusion in this paper. The experimental results show that compared with the existing mainstream algorithms, the algorithm in this paper has good subjective evaluation, natural image enhancement, no distortion in color, and high network robustness. In terms of objective metrics, the PSNR, SSIM, MSE, image mean value and image information entropy of the algorithms in this paper are significantly improved over other algorithms. Among them, in the dataset LOL with reference images, PSNR, SSIM and MSE are improved by about 61.55, 9.42 and 861.7% respectively. In the datasets Exdark and DARK FACE without reference images, the image mean and image information entropy are improved by about 20.728 and 2.31% respectively.
Similar content being viewed by others
Data Availability Statement
LOL dataset: BMVC2018 Deep Retinex Decomposition (daooshee.github.io) Exdark dataset: GitHub—cs-chan/Exclusively-Dark-Image-Dataset: Exclusively Dark (ExDARK) dataset which to the best of our knowledge, is the largest collection of low-light images taken in very low-light environments to twilight (i.e. 10 different conditions) to-date with image class and object level annotations. DARK FACE dataset: DARK FACE: Face Detection in Low Light Condition (flyywh.github.io).
References
Yan YJ, Zhang YP, Jia ZZ et al (2021) Review of low illumination image enhancement technology based on deep learning [J]. Wirel Int Technol 18(01):77–80
Rera AM (2004) Realization of the contrast limited adaptive histogram equalization (CLAHE) for real-time image enhancement[J]. J VLSI Sig Proc 38(1):35–44
Ibrahim H, Kong NSP (2007) Brightness preserving dynamic histogram equalization for image contrast enhancement[J]. IEEE Trans Consum Electr 53(4):1752–1758
Kim JY, Kim LS, Hwang SH (1999) An advanced contrast enhancement using partially overlapped sub-block histogram equalization. J Korean Inst Telem Electr S 36(12):58–66
Liu QZ, Liu Q (2015) Adaptive enhancement algorithm for low illumination images based on wavelet transform [J]. Chin J Lasers 42(02):280–286
Jia XY (2019) Noise reduction and enhancement algorithm of night low illumination image based on wavelet transform [J]. Inform Technol Inform 02:107–109
Demirel H, Ozcinar C, Anbarjafari G (2010) Satellite image contrast enhancement using discrete wavelet transform and singular value decomposition[J]. IEEE Geosci Remote Sens Lett 7(2):333–337
Bhutada GG, Anand RS, Saxena SC (2011) Edge preserved image enhancement using adaptive fusion of images denoised by wavelet and curvelet transform[J]. Digital Signal Process 21(1):118–130
Fu ZF, Zhu H (2013) Enhancment algorithms for low-illumination image based on wavelet transform [J]. J Shanxi Univ 36(04):497–504
Guo Y, Ke X, Ma J, Zhang J (2019) A pipeline neural network for low-light image enhancement. IEEE Access 7:13737–13744
Jobson DJ, Rahman ZU, Woodell GA (1997) Properties and performance of a center/surround retinex[J]. IEEE Trans Image Process 6(3):451–462
Rahman ZU, Jobson DJ, Woodell GA (1996). Multi-scale retinex for color image enhancement. In: Proceedings of 3rd IEEE international conference on image processing. 3, p. 1003-1006 IEEE
Fu X, Zeng D, Huang Y, Zhang XP, Ding X (2016) A weighted variational model for simultaneous reflectance and illumination estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition p. 2782-2790
Zhao HY et al (2014) A Retinex algorithm for night color image enhancement by MRF. Opt Precis Eng 22(04):1048–1055
Zhang J, Zhou PC, Que MG (2018) Low-light image enhancement based on directional total variation retinex. J Comp-Aided Des Comp Graph 30(10):1943–1953
Guo X, Li Y, Ling H (2017) LIME: low-light image enhancement via illumination map estimation. IEEE Trans Image Process 26(2):982–993
Li C, Guo J, Porikli F, Pang Y (2018) LightenNet: a convolutional neural network for weakly illuminated image enhancement. Pattern Recognit Lett 104:15–22
Lore KG, Akintayo A, Sarkar S (2017) LLNet: A deep autoencoder approach to natural low-light image enhancement. Pattern Recognit. 61:650–662
Cai J, Gu S, Zhang L (2018) Learning a deep single image contrast enhancer from multi-exposure images[J]. IEEE Trans Image Process 27(4):2049–2062
Yu C, Dexiang D, Jia Y, Ci’en FAN (2019) Weakly illuminated image enhancement algorithm based on convolutional neural network. J Comp Appl 39(4):1162
Ren X, Li M, Cheng W H, et al (2018) Joint enhancement and denoising method via sequential decomposition[C]. 2018 IEEE International symposium on circuits and systems (ISCAS). IEEE
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
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 p. 1632-1640
Jiang Y, Gong X, Liu D, Cheng Y, Fang C, Shen X, Wang Z (2021) EnlightenGAN: deep light enhancement without paired supervision. IEEE Trans Image Process 30:2340–2349
Hongqiang M, Shiping M, Yuelei X, Mingming Z. Low light image enhancement based on deep convolutional neural network. Acta Optica Sinica. 39(2):021
Chen ZM, Peng LX (2018) The principle and practice of deep learning. post & Telecom Press: Beijing, China, p. 23-92
Yu F, Koltun V (2016) Multi-scale context aggregation by dilated convolutions[C]. ICLR
He K, Zhang X, Ren S et al. (2016) Deep residual learning for image recognition [J]. 2016 IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, NV, USA, p. 770–778
Li LZ (2019) Getting started with OpenCV: face Python[M].Bei Jing: Publishing house of electronics industry
Wei C, Wang W, Yang W, et al (2018) Deep retinex decomposition for low-light enhancement[J]
Cheng HD, Shi XJ (2004) A simple and effective histogram equalization approach to image enhancement[J]. Digital Signal Process 14(2):158–170
Yang W et al (2020) Advancing image understanding in poor visibility environments: a collective benchmark study,". IEEE Trans Image Process 29:5737–5752. https://doi.org/10.1109/TIP.2020.2981922
Funding
This work was supported by the science and Technology Department of Jilin Province, China (No. 20180623039TC).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
This work does not include any research on human and animals, and there is no conflict of interest. All authors are aware of this submission.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Wang, X., Piao, Y. & Wang, Y. A dark image enhancement method based on multiscale features and dilated residual networks. Neural Process Lett 54, 5525–5543 (2022). https://doi.org/10.1007/s11063-022-10872-z
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-022-10872-z