Computer Engineering and Applications ›› 2022, Vol. 58 ›› Issue (8): 214-220.DOI: 10.3778/j.issn.1002-8331.2010-0011

• Graphics and Image Processing • Previous Articles     Next Articles

Low Illumination Image Enhancement Method Based on DenseNet GAN

WANG Zhaoqian, KONG Weiwei, TENG Jinbao, TIAN Qiaoxin   

  1. 1.Xi’an University of Posts and Telecommunications, Xi’an 710121, China
    2.Shaanxi Provincial Key Laboratory of Network Data Analysis and Intelligent Processing, Xi’an 710121, China
  • Online:2022-04-15 Published:2022-04-15

DenseNet生成对抗网络低照度图像增强方法

王照乾,孔韦韦,滕金保,田乔鑫   

  1. 1.西安邮电大学,西安 710121
    2.陕西省网络数据分析与智能处理重点实验室,西安 710121

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