[1]张 敏,黄 刚,陈啟超.基于残差学习的图像超分辨率重构方法[J].计算机技术与发展,2021,31(08):51-56.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 009]
　ZHANG Min,HUANG Gang,CHEN Qi-chao.A Super-resolution Image Reconstruction Method Based onResidual Learning[J].,2021,31(08):51-56.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 009]
点击复制

基于残差学习的图像超分辨率重构方法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
31
期数:
2021年08期
页码:
51-56
栏目:
图形与图像
出版日期:
2021-08-10

文章信息/Info

Title:
A Super-resolution Image Reconstruction Method Based onResidual Learning
文章编号:
1673-629X(2021)08-0051-06
作者:
张 敏; 黄 刚; 陈啟超
南京邮电大学 计算机学院,江苏 南京 210046
Author(s):
ZHANG Min; HUANG Gang; CHEN Qi-chao
School of Computer,Nanjing University of Posts and Telecommunications,Nanjing 210046,China
关键词:
深度学习; 图像超分辨率; 反卷积; 非线性映射; 残差学习
Keywords:
deep learning; image super-resolution; deconvolution; nonlinear mapping; residual learning
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2021. 08. 009
摘要:
图像超分辨率重构是计算机视觉领域中的一个经典问题,旨在通过算法将一幅或者多幅低分辨率图像转化为高分辨率图像。 近年来,基于深度学习的单幅图像超分辨率重构算法得到了广泛的应用。 针对多数网络存在的学习能力较弱、训练时间较长以及重建图像质量有待提升等问题,提出一种基于残差学习的图像超分辨率重构方法。 网络通过级联深度卷积网络对图像进行特征提取,引入残差学习获得深层次的纹理细节信息,并加快网络的收敛速度,避免梯度爆炸和梯度消失,通过反卷积层对特征图像进行上采样,重建出与目标图像尺寸相同的高分辨率图像。 在 Set5、Set14 等测试集中,使用峰值信噪比(PSNR)和结构相似性(SSIM)作为所提算法的评价指标,同时对比 SRCNN、FSRCNN 以及 VDSR 等方法均重建出了效果更好的图像。 实验结果表明,该方法能够有效地提高特征信息的利用率,生成具有丰富细节且清晰的高分辨率图像。
Abstract:
Image super-resolution reconstruction is a classic problem in the field of computer vision,which aims to transform one or more low-resolution images into high-resolution images through algorithms. In recent years,a single image super-resolution reconstruction algorithm based on deep learning has been widely used. Aiming at the problems of weak learning ability,long training time,and the quality of reconstructed images in most networks,we propose an image super-resolution reconstruction method based on residual learning. The network uses the cascaded deep convolutional network to extract features of the image,introduces residual learning to obtain deep texture detail information,and accelerates the convergence speed of the network, avoids gradient explosion and gradient disappearance, and uploads the feature image through the deconvolution layer sampling to reconstruct a high-resolution image with the same size as the target image. In the test sets such as Set5 and Set14,peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) are used as the eval鄄uation indicators of the proposed algorithm. At the same time,compared with SRCNN,FSRCNN and VDSR,they have reconstructed better images. Experiment shows that the proposed method can effectively improve the utilization of feature information and generate clear and high-resolution images with rich details.

相似文献/References:

[1]葛广重,杨敏.基于稀疏表示的单幅图像超分辨率重建[J].计算机技术与发展,2013,(09):113.
　GE Guang-zhong,YANG Min.Single Image Super-resolution Reconstruction Based on Sparse Representation[J].,2013,(08):113.
[2]陈强锐,谢世朋.基于深度学习的肺部肿瘤检测方法[J].计算机技术与发展,2018,28(04):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
　CHEN Qiang-rui,XIE Shi-peng.Lung Cancer Detection Method Based on Deep Learning[J].,2018,28(08):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
[3]施泽浩,赵启军.基于全卷积网络的目标检测算法[J].计算机技术与发展,2018,28(05):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
　SHI Ze-hao,ZHAO Qi-jun.Object Detection Algorithm Based on Fully Convolutional Neural Network[J].,2018,28(08):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
[4]黄法秀,张世杰,吴志红,等.数据增广下的人脸识别研究[J].计算机技术与发展,2020,30(03):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
　HUANG Fa-xiu,ZHANG Shi-jie,WU Zhi-hong,et al.Research on Face Recognition Based on Data Augmentation[J].,2020,30(08):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
[5]陈浩翔,蔡建明,刘铿然,等. 手写数字深度特征学习与识别[J].计算机技术与发展,2016,26(07):19.
　CHEN Hao-xiang,CAI Jian-ming,LIU Keng-ran,et al. Deep Learning and Recognition of Handwritten Numeral Features[J].,2016,26(08):19.
[6]高翔,陈志,岳文静,等.基于视频场景深度学习的人物语义识别模型[J].计算机技术与发展,2018,28(06):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
　GAO Xiang,CHEN Zhi,YUE Wen-jing,et al.Human Semantic Recognition Model Based on Video Scene Deep Learning[J].,2018,28(08):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
[7]贺飞翔,赵启军. 基于深度学习的头部姿态估计[J].计算机技术与发展,2016,26(11):1.
　HE Fei-xiang,ZHAO Qi-jun. Head Pose Estimation Based on Deep Learning[J].,2016,26(08):1.
[8]徐 融,邱晓晖.一种改进的 YOLO V3 目标检测方法[J].计算机技术与发展,2020,30(07):30.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 007]
　XU Rong,QIU Xiao-hui.An Improved YOLO V3 Object Detection[J].,2020,30(08):30.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 007]
[9]曾志平[] [],萧海东[],张新鹏[]. 基于DBN的金融时序数据建模与决策[J].计算机技术与发展,2017,27(04):1.
　ZENG Zhi-ping[] [],XIAO Hai-dong[],ZHANG Xin-peng[]. Modeling and Decision-making of Financial Time Series Data with DBN[J].,2017,27(08):1.
[10]李全兵,文 钊*,田艳梅*,等.基于 WGAN 的音频关键词识别研究[J].计算机技术与发展,2021,31(08):26.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 005]
　LI Quan-bing,WEN Zhao *,TIAN Yan-mei *,et al.Research on Audio Keywords Recognition Based on WassersteinGenerative Adversarial Network[J].,2021,31(08):26.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 005]
[11]倪申龙,曾接贤,周世健.整体车牌图像超分辨率重建研究[J].计算机技术与发展,2019,29(04):195.[doi:10. 3969 / j. issn. 1673-629X. 2019. 04. 039]
　NI Shen-long,ZENG Jie-xian,ZHOU Shi-jian.Study on Reconstruction of Overall Image of License Plate[J].,2019,29(08):195.[doi:10. 3969 / j. issn. 1673-629X. 2019. 04. 039]

更新日期/Last Update: 2021-08-10