Low Illumination Image Enhancement Method Based on DenseNet GAN

doi:10.3778/j.issn.1002-8331.2010-0011

Abstract

Abstract: Aiming at the problems of low SNR, low resolution and low illumination in low illumination environment, a low illumination image enhancement method based on DenseNet generation countermeasure network is proposed. Firstly, the DenseNet framework is used to establish the generator network, and PatchGAN is used as the discriminator network. Secondly, the low illumination image is transferred into the generator network to generate the illumination enhanced image, and the discriminator network is used to supervise the enhancement effect of the generator on the low illumination image. Through the game between the generator and the discriminator, the network weight is continuously optimized, and finally the generator has good enhancement effect on low illumination image. Experimental results show that, compared with the existing mainstream methods, this method not only has obvious advantages in brightness enhancement and clarity restoration of low illumination images, but also has significant advantages in objective evaluation indexes of image quality such as peak signal-to-noise ratio and structure similarity.

Key words: low illumination image enhancement, Generative Adversarial Nets（GAN）, DenseNet, PatchGAN

摘要： 针对低照度环境下采集图像存在低信噪比、低分辨率和低照度的问题，提出了一种基于稠密连接网络（DenseNet）生成对抗网络的低照度图像增强方法。利用DenseNet框架建立生成器网络，并将PatchGAN作为判别器网络；将低照度图像传入生成器网络生成照度增强图像，同时利用判别器网络负责监督生成器对低照度图像的增强效果，通过生成器和判别器二者间的博弈不断优化网络权重，最终使得生成器对低照度图像具有较好的增强效果。实验结果表明，该方法与现有主流方法相比较，不仅在对低照度图像亮度增强、清晰度还原等方面优势明显，且在峰值信噪比和结构相似度等图像质量客观评价指标方面也具有显著的优势。

关键词: 低照度图像增强, 生成对抗网络, 稠密连接网络, PatchGAN

WANG Zhaoqian, KONG Weiwei, TENG Jinbao, TIAN Qiaoxin. Low Illumination Image Enhancement Method Based on DenseNet GAN[J]. Computer Engineering and Applications, 2022, 58(8): 214-220.

王照乾, 孔韦韦, 滕金保, 田乔鑫. DenseNet生成对抗网络低照度图像增强方法[J]. 计算机工程与应用, 2022, 58(8): 214-220.

References

[1] PIZER S M，AMBURN E P，AUSTIN J D，et al.Adaptive histogram equalization and its variations[J].Computer Vision Graphics and Image Processing，1987，39（3）：355-368.
[2] LAND E H.The retinex theory of color vision[J].Scientific American，1977，237（6）：108-128.
[3] JOBSON D J，RAHMAN Z，WOODELL G A.Properties and performance of a center/surround Retinex[J].IEEE Transactions on Image Processing，1997，6（3）：451-462.
[4] JOBSON D J，RAHMAN Z，WOODELL G A.A multiscale retinex for bridging the gap between color images and the observation of scences[J].IEEE Transactions on Image Processing，1997，6（7）：965-976.
[5] FU X Y，ZENG D，HUANG Y，et al.A fusion-based enhancing method for weakly illuminated images[J].Signal Processing，2016，129（C）：82-96.
[6] GUO X J，LI Y，LING H B.LIME：low-light image enhancement via illuminationmap estimation[J].IEEE Transactions on Image Processing，2017，26（2）：982-993.
[7] YING Z Q，LI G，REN Y，et al.A new low-light image enhancement algorithm using camera response model[C]//IEEE International Conference on Computer Vision（ICCV），2017：3015-3022.
[8] REN X，LI M，CHENG W H，et al.Joint enhancement and denoising method via sequential decomposition[C]//IEEE International Symposium on Circuits and Systems，2018：1-5.
[9] LORE K G，AKINTAYO A，SARKAR S.LLNet：a deep autoencoder approach to natural low-light image enhancement[J].Pattern Recognition，2017，61：650-662.
[10] TAO L，ZHU C，XIANG G Q，et al.LLCNN：a convolutional neural network for low-light image enhancement[C]//Proceedings of 2017 IEEE Visual Communications and Image Processing，2017：1-4.
[11] LI C，GUO J，PORIKLI F，et al.LightenNet：a convolutional neural network for weakly illuminated image enhancement[J].Pattern Recognition Letters，2018，104：15-22.
[12] 马红强，马时平，许悦雷，等.基于深度卷积神经网络的低照度图像增强[J].光学学报，2019，39（2）：99-108.
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）：99-108.
[13] GOODFELLOW I J，POUGET-ABADIE J，MIRZA M，et al.Generative adversarial nets[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems，2014：2672-2680.
[14] ISOLA P，ZHU J Y，ZHOU T，et al.Image-to-image translation with conditional adversarial networks[C]//Proceedings of the IEEE Computer Vision and Pattern Recognition，2017：1125-1134.
[15] HUANG G，LIU Z，WEINBERGER K Q，et al.Densely connected convolutional networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：1-8.
[16] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：770-778.
[17] CAI J R，GU S H，ZHANG L.Learning a deep single image contrast enhancer from multi-exposure images[J].IEEE Transactions on Image Processing，2018，27（4）：2049-2062.
[18] MANNOS J，SAKRISON D.The effects of a visual fidelity criterion of the encoding of images[J].IEEE Transactions on Information Theory，1974，20（4）：525-536.
[19] WANG Z，BOVIK A C，SHEIKH H R，et al.Image quality assessment：from error visibility to structural similarity[J].IEEE Transactions on Image Processing，2004，13（4）：600-612.