高级搜索

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于多尺度稠密残差网络的JPEG压缩伪迹去除方法

陈书贞 张祎俊 练秋生

陈书贞, 张祎俊, 练秋生. 基于多尺度稠密残差网络的JPEG压缩伪迹去除方法[J]. 电子与信息学报, 2019, 41(10): 2479-2486. doi: 10.11999/JEIT180963
引用本文: 陈书贞, 张祎俊, 练秋生. 基于多尺度稠密残差网络的JPEG压缩伪迹去除方法[J]. 电子与信息学报, 2019, 41(10): 2479-2486. doi: 10.11999/JEIT180963
Shuzhen CHEN, Yijun ZHANG, Qiusheng LIAN. JPEG Compression Artifacts Reduction Algorithm Based on Multi-scale Dense Residual Network[J]. Journal of Electronics & Information Technology, 2019, 41(10): 2479-2486. doi: 10.11999/JEIT180963
Citation: Shuzhen CHEN, Yijun ZHANG, Qiusheng LIAN. JPEG Compression Artifacts Reduction Algorithm Based on Multi-scale Dense Residual Network[J]. Journal of Electronics & Information Technology, 2019, 41(10): 2479-2486. doi: 10.11999/JEIT180963

基于多尺度稠密残差网络的JPEG压缩伪迹去除方法

doi: 10.11999/JEIT180963
基金项目: 国家自然科学基金(61471313),河北省自然科学基金(2019203318)
详细信息
    作者简介:

    陈书贞:女,1968年生,副教授,研究方向为图像处理、压缩感知、深度学习、相位恢复

    张祎俊:女,1994年生,硕士生,研究方向为深度学习,JPEG压缩伪迹去除

    练秋生:男,1969年生,教授,博士生导师,研究方向为稀疏表示、深度学习、压缩感知及相位恢复

    通讯作者:

    练秋生 lianqs@ysu.edu.cn

  • 中图分类号: TN911.73

JPEG Compression Artifacts Reduction Algorithm Based on Multi-scale Dense Residual Network

Funds: The National Natural Science Foundation of China (61471313), The Natural Science Foundation of Hebei Province (2019203318)
  • 摘要: JPEG在高压缩比的情况下,解压缩后的图像会产生块效应、边缘振荡效应和模糊,严重影响了图像的视觉效果。为了去除JPEG压缩伪迹,该文提出了多尺度稠密残差网络。首先把扩张卷积引入到残差网络的稠密块中,利用不同的扩张因子,使其形成多尺度稠密块;然后采用4个多尺度稠密块将网络设计成包含2条支路的结构,其中后一条支路用于补充前一条支路没有提取到的特征;最后采用残差学习的方法来提高网络的性能。为了提高网络的通用性,采用具有不同压缩质量因子的联合训练方式对网络进行训练,针对不同压缩质量因子训练出一个通用模型。经实验表明,该文方法不仅具有较高的JPEG压缩伪迹去除性能,且具有较强的泛化能力。
  • 图  1  多尺度稠密残差网络

    图  2  由扩张因子$s = i$的扩张卷积组成的稠密块

    图  3  多尺度稠密残差网络中每个分支的输出图像

    图  4  QF为10时,图像sailing3在各个算法中的视觉比较

    表  1  ARCNN的4个模型在LIVE1数据集上的PSNR(dB)对比

    模型QF
    10203040
    JPEG27.7730.0731.4132.35
    ARCNN(${\rm{QF}} = 10$)28.9630.7931.5131.90
    ARCNN(${\rm{QF}} = 20$)28.7831.3032.5333.30
    ARCNN(${\rm{QF}} = 30$)28.6031.2532.6933.61
    ARCNN(${\rm{QF}} = 40$)28.4831.1432.6233.63
    下载: 导出CSV

    表  2  本文方法在LIVE1数据集上的PSNR(dB)/SSIM对比

    方法QF
    10203040
    JPEG27.77/0.790530.07/0.868331.41/0.900032.35/0.9173
    ARCNN28.96/0.821731.30/0.887132.69/0.916133.63/0.9303
    L4 Residual29.08/0.824131.42/0.890032.80/0.917433.78/0.9322
    L8 Residual31.51/0.8911
    DnCNN-329.20/0.826231.59/0.893632.98/0.920433.96/0.9346
    本文方法29.49/0.832931.81/0.895233.08/0.919634.14/0.9367
    下载: 导出CSV

    表  3  本文方法在Classic5数据集上的PSNR(dB)/SSIM对比

    方法QF
    10203040
    JPEG27.82/0.780030.12/0.854131.48/0.884432.43/0.9011
    ARCNN29.04/0.810831.16/0.869132.52/0.896333.34/0.9098
    DnCNN-329.40/0.820131.63/0.877532.90/0.901133.77/0.9141
    本文方法29.68/0.827531.87/0.879833.03/0.901333.95/0.9166
    下载: 导出CSV

    表  4  本文方法在LIVE1数据集上的PSNR(dB)/SSIM对比

    方法QF
    15253545
    JPEG29.13/0.840230.81/0.886931.93/0.910132.78/0.9241
    DnCNN-330.61/0.869732.35/0.909433.53/0.928734.39/0.9400
    本文方法30.83/0.873332.50/0.909533.68/0.930334.56/0.9416
    下载: 导出CSV

    表  5  不同尺度的选择在LIVE1数据集上的PSNR(dB)/SSIM对比

    不同尺度QF
    10152025
    单一尺度($3 \times 3$)29.42/0.830930.78/0.871931.75/0.894232.46/0.9086
    单一尺度($5 \times 5$)29.44/0.831630.79/0.871931.76/0.894532.46/0.9090
    本文方法29.49/0.832930.83/0.873331.81/0.895232.50/0.9095
    下载: 导出CSV

    表  6  不同网络层数在LIVE1数据集上的PSNR(dB)/SSIM对比

    不同层数QF
    10152025
    Dense329.45/0.831830.79/0.871431.77/0.894732.47/0.9090
    Dense429.47/0.832530.81/0.872831.79/0.895032.49/0.9092
    Dense529.49/0.832930.83/0.873331.81/0.895232.50/0.9095
    Dense629.47/0.832430.81/0.873531.79/0.895132.49/0.9099
    下载: 导出CSV

    表  7  使用普通块和稠密块在LIVE1数据集上的PSNR(dB)/SSIM对比

    方法QF
    10152025
    普通块29.39/0.830330.75/0.871231.71/0.893832.41/0.9081
    稠密块29.49/0.832930.83/0.873331.81/0.895232.50/0.9095
    下载: 导出CSV
  • FOI A, KATKOVNIK V, and EGIAZARIAN K. Pointwise shape-adaptive DCT for high-quality denoising and deblocking of grayscale and color images[J]. IEEE Transactions on Image Processing, 2007, 16(5): 1395–1411. doi: 10.1109/TIP.2007.891788
    YOO S B, CHOI K, and RA J B. Post-processing for blocking artifact reduction based on inter-block correlation[J]. IEEE Transactions on Multimedia, 2014, 16(6): 1536–1548. doi: 10.1109/TMM.2014.2327563
    ZHAO Chen, ZHANG Jian, MA Siwei, et al. Reducing image compression artifacts by structural sparse representation and quantization constraint prior[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2017, 27(10): 2057–2071. doi: 10.1109/TCSVT.2016.2580399
    吕晓琪, 吴凉, 谷宇, 等. 基于深度卷积神经网络的低剂量CT肺部去噪[J]. 电子与信息学报, 2018, 40(6): 1353–1359. doi: 10.11999/JEIT170769

    LÜ Xiaoqi, WU Liang, GU Yu, et al. Low dose CT lung denoising model based on deep convolution neural network[J]. Journal of Electronics &Information Technology, 2018, 40(6): 1353–1359. doi: 10.11999/JEIT170769
    DONG Chao, LOY C C, HE Kaiming, et al. Image super-resolution using deep convolutional networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(2): 295–307. doi: 10.1109/TPAMI.2015.2439281
    郭智, 宋萍, 张义, 等. 基于深度卷积神经网络的遥感图像飞机目标检测方法[J]. 电子与信息学报, 2018, 40(11): 2684–2690. doi: 10.11999/JEIT180117

    GUO Zhi, SONG Ping, ZHANG Yi, et al. Aircraft detection method based on deep convolutional neural network for remote sensing images[J]. Journal of Electronics &Information Technology, 2018, 40(11): 2684–2690. doi: 10.11999/JEIT180117
    REN Shaoqing, HE Kaiming, GIRSHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137–1149. doi: 10.1109/TPAMI.2016.2577031
    BADRINARAYANAN V, KENDALL A, and CIPOLLA R. Segnet: A deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12): 2481–2495. doi: 10.1109/TPAMI.2016.2644615
    DONG Chao, DENG Yubin, LOY C C, et al. Compression artifacts reduction by a deep convolutional network[C]. 2015 IEEE International Conference on Computer Vision, Santiago, Chile, 2015: 576-584. doi: 10.1109/ICCV.2015.73.
    SVOBODA P, HRADIS M, BARINA D, et al. Compression artifacts removal using convolutional neural networks[J/OL]. arXiv preprint arXiv: 1605.00366. http://arxiv.org/abs/1605.00366, 2016.
    ZHANG Kai, ZUO Wangmeng, CHEN Yunjin, et al. Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising[J]. IEEE Transactions on Image Processing, 2017, 26(7): 3142–3155. doi: 10.1109/TIP.2017.2662206
    KIM Y, HWANG I, and CHO N I. A new convolutional network-in-network structure and its applications in skin detection, semantic segmentation, and artifact reduction[J/OL]. arXiv preprint arXiv: 1701.06190. http://arxiv.org/abs/1701.06190, 2017.
    SZEGEDY C, LIU Wei, JIA Yangqing, et al. Going deeper with convolutions[C]. 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, 2015: 1–9.
    LIU Pengju, ZHANG Hongzhi, ZHANG Kai, et al. Multi-level Wavelet-CNN for image restoration[C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Salt Lake City, USA, 2018: 886–895.
    RONNEBERGER O, FISCHER P, and BROX T. U-Net: Convolutional networks for biomedical image segmentation[C]. The 18th International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 2015: 234–241.
    GUO Jun and CHAO Hongyang. One-to-many network for visually pleasing compression artifacts reduction[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 4867–4876.
    GALTERI L, SEIDENARI L, BERTINI M, et al. Deep generative adversarial compression artifact removal[C]. 2017 IEEE International Conference on Computer Vision, Venice, Italy, 2017: 4836–4845.
    HUANG Gao, LIU Zhuang, WEINBERGER K Q, et al. Densely connected convolutional networks[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017, 1: 2261–2269.
    ZHANG Kai, ZUO Wangmeng, GU Shuhang, et al. Learning deep CNN denoiser prior for image restoration[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017, 2: 2808–2817.
    KRIZHEVSKY A, SUTSKEVER I, and HINTON G E. ImageNet classification with deep convolutional neural networks[C]. The 25th International Conference on Neural Information Processing Systems, Lake Tahoe, USA, 2012: 1097–1105.
  • 加载中
图(4) / 表(7)
计量
  • 文章访问数:  4296
  • HTML全文浏览量:  1415
  • PDF下载量:  81
  • 被引次数: 0
出版历程
  • 收稿日期:  2018-10-15
  • 修回日期:  2019-03-05
  • 网络出版日期:  2019-04-02
  • 刊出日期:  2019-10-01

目录

    /

    返回文章
    返回