[1]贾玉福,胡胜红,刘文平,等.使用条件生成对抗网络的自然图像增强方法[J].南京师范大学学报(自然科学版),2019,42(03):88-95.[doi:10.3969/j.issn.1001-4616.2019.03.012]
　Jia Yufu,Hu Shenghong,Liu Wenping,et al.Wild Image Enhancement with Conditional Generative Adversarial Network[J].Journal of Nanjing Normal University(Natural Science Edition),2019,42(03):88-95.[doi:10.3969/j.issn.1001-4616.2019.03.012]
点击复制

使用条件生成对抗网络的自然图像增强方法()
分享到：

《南京师范大学学报》（自然科学版）[ISSN:1001-4616/CN:32-1239/N]

卷:
第42卷
期数:
2019年03期
页码:
88-95
栏目:
·全国机器学习会议论文专栏·
出版日期:
2019-09-30

文章信息/Info

Title:
Wild Image Enhancement with Conditional Generative Adversarial Network
文章编号:
1001-4616(2019)03-0088-08
作者:
贾玉福1; 胡胜红2; 刘文平1; 王 超2; 向书成2
(1.湖北经济学院信息管理与统计学院,湖北 武汉 430205)(2.湖北经济学院信息与通信工程学院,湖北 武汉 430205)
Author(s):
Jia Yufu1; Hu Shenghong2; Liu Wenping1; Wang Chao2; Xiang Shucheng2
(1.Information Management and Statistics School,Hubei University of Economics,Wuhan 430205,China)(2.Information and Communication Engineering School,Hubei University of Economics,Wuhan 430205,China)
关键词:
图像增强; 生成对抗网络; 深度学习; 图像质量
Keywords:
image enhancement; generative adversarial network; deep learning; image quality
分类号:
TP391
DOI:
10.3969/j.issn.1001-4616.2019.03.012
文献标志码:
A
摘要:
自然图像增强是计算机视觉领域中的一个研究热点. 针对以往图像增强方法计算过程复杂和参数需手工设置等缺陷,提出一种基于条件生成对抗模型的图像增强(enhancement with conditional generative adversarial networks,E-CGAN)方法. 分别构建生成式神经网络和判别式神经网络,其中,生成模型直接对图像进行处理生成最终增强的图片结果,判别模型在训练阶段对生成模型构建对抗型损失函数,优化生成模型的参数. 在生成模型的结构中,加入L1距离误差函数作为生成模型的约束,并提出连续多尺度跨层连接方式,加快网络的训练速度,提高生成模型的准确率. 在图像清晰度增强,灰度图像着色两个图像增强问题上进行实验,结果表明,E-CGAN可以有效地保留图像特征,PSNR和SSIM质量平均提高9%和5%.
Abstract:
Wild image enhancement technology is a hotspot in the field of computer vision. To overcome the defects on complexity of calculation and manual setting parameters of the conventional image enhancement methods,a novel image enhancement method with conditional generative adversarial network(E-CGAN)has been proposed. The generative neural network and the discriminant neural network are constructed respectively,where the generative model is used to generate the final images and the discriminant model is employed to construct the confrontation loss function in the training stage,so as to optimize the parameters of the two models. In the structure of the generative model,a successive-multiple skip connection method constrained by L1 error function is proposed,which speeds up the training speed of the network and improves the accuracy of the generative model. Two implementations on image sharpening and colorization have been implemented to evaluate the effectiveness of the proposed method,the experimental results show that E-CGAN can effectively highlight the characteristics of the image,and better quality promotion achieves up to 9% and 5% both on PSNR and SSIM index.

参考文献/References:

[1] REINHARD E,ASHIKHMIN M,GOOCH B,et al. Color transfer between images[J]. IEEE computer graphics & applications,2002,21(5):34-41.
[2]WELSH T,ASHIKHMIN M,MUELLER K. Transferring color to greyscale images[J]. ACM Frans Graph,2002,21(3):277-280.
[3]PANETTA K,WHARTON E J,ZHOU Y,et al. Parameterized logarithmic framework for image enhancement[J]. IEEE transactions on systems,man,and cybernetics,Part B:cybernetics,2011,41(2):460-473.
[4]ZHANG Q,NIE Y,ZHANG L,et al. Underexposed video enhancement via perception-driven progressive fusion[J]. IEEE transactions on image processing,2016,22(6):1773-1785.
[5]GOODFELLOW I J,POUGET A J,MIRZA M,et al. Generative adversarial nets[C]//2014 International Conference on Neural Information Processing Systems. Canada:MIT Press,2014:2672-2680.
[6]CRESWELL A,WHITE T,DUMOULIN V,et al. Generative adversarial networks:an overview[J]. IEEE signal processing magazine,2018,35(1):53-65.
[7]DENTON E,CHINTALA S,SZLAM A,et al. Deep generative image models using a laplacian pyramid of adversarial networks[C]//2015 Advances in Neural Information Processing Systems(NIPS). Canada:ACM,2015:1486-1494.
[8]GUPTA P,SRIVASTAVA P,BHARDWAJ S,et al. A modified PSNR metric based on HVS for quality assessment of color images[C]//2011 International Conference on Communication and Industrial Application. Kolkata,West Bengal:IEEE,2012:1-4.
[9]LONG J,SHELHAMER E,DARRELL T. Fully convolutional networks for semantic segmentation[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Boston,Ma:IEEE,2015:3431-3440.
[10]PATHAK D,KRAHENBUHL P,DONAHUE J,et al. Context encoders:feature learning by inpainting[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR). NV:IEEE,2016:2536-2544.
[11]RUSSAKOVSKY O,DENG J,SU H,et al. ImageNet large scale visual recognition challenge[J]. International journal of computer vision,2015,115(3):211-252.
[12]CHENG Z,YANG Q,SHENG B. Deep colorization[C]//IEEE International Conference on Computer Vision. Santiago:IEEE,2015:415-423.
[13]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.
[14]CHENG H D,SHI X J. A simple and effective histogram equalization approach to image enhancement[J]. Digital signal processing,2004,14(2):158-170.
[15]YAN Z,ZHANG H,PARIS S,et al. Automatic photo adjustment using deep neural networks[J]. Acm transactions on graphics,2016,35(2):11.
[16]HE K,ZHANG X,REN S,et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Las Vegas,NV:IEEE,2016:770-778.
[17]CHAI C,LIAO J,ZOU N,et al. A one-to-many conditional generative adversarial network framework for multiple image-to-image translations[J]. Multimedia tools and applications. 2018,77(17):22339-22366.

相似文献/References:

[1]程 科,汪正霞,孙 玮.基于小波系数相关性的MRI图像像素点分类处理算法[J].南京师范大学学报(自然科学版),2014,37(01):41.
　Cheng Ke,Wang Zhengxia,Sun Wei.A Pixel Classification Method in MRI Enhancement Based on Wavelet Coefficient[J].Journal of Nanjing Normal University(Natural Science Edition),2014,37(03):41.
[2]尤鸣宇,韩 煊.基于样本扩充的小样本车牌识别[J].南京师范大学学报(自然科学版),2019,42(03):1.[doi:10.3969/j.issn.1001-4616.2019.03.001]
　You Mingyu,Han Xuan.Small Sample License Plate Recognition Based on Sample Expansion[J].Journal of Nanjing Normal University(Natural Science Edition),2019,42(03):1.[doi:10.3969/j.issn.1001-4616.2019.03.001]

备注/Memo

备注/Memo:
收稿日期:2019-07-05.基金项目:国家自然科学基金(61572012)、教育部人文社科项目(18YJCZH050)、湖北省自然科学基金(D20182202)、教育厅科研计划(2018CFB721). 通讯联系人:胡胜红,博士,副教授,研究方向:基于内容的视频检索与自适应传输、深度学习. E-mail:wuhanhush@126.com
更新日期/Last Update: 2019-09-30