基于多尺度稠密殘差網(wǎng)絡(luò)的JPEG壓縮偽跡去除方法

陳書貞; 張祎俊; 練秋生

doi:10.11999/JEIT180963

基于多尺度稠密殘差網(wǎng)絡(luò)的JPEG壓縮偽跡去除方法

doi: 10.11999/JEIT180963

1.
燕山大學(xué)信息科學(xué)與工程學(xué)院秦皇島 066004
2.
河北省信息傳輸與信號(hào)處理重點(diǎn)實(shí)驗(yàn)室秦皇島 066004

基金項(xiàng)目: 國(guó)家自然科學(xué)基金(61471313)，河北省自然科學(xué)基金(2019203318)

詳細(xì)信息

作者簡(jiǎn)介:
陳書貞：女，1968年生，副教授，研究方向?yàn)閳D像處理、壓縮感知、深度學(xué)習(xí)、相位恢復(fù)

張祎?。号?994年生，碩士生，研究方向?yàn)樯疃葘W(xué)習(xí)，JPEG壓縮偽跡去除

練秋生：男，1969年生，教授，博士生導(dǎo)師，研究方向?yàn)橄∈璞硎?、深度學(xué)習(xí)、壓縮感知及相位恢復(fù)

通訊作者:
練秋生 lianqs@ysu.edu.cn

中圖分類號(hào): TN911.73
計(jì)量
- 文章訪問(wèn)數(shù): 4323
- HTML全文瀏覽量: 1444
- PDF下載量: 81
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2018-10-15
- 修回日期: 2019-03-05
- 網(wǎng)絡(luò)出版日期: 2019-04-02
- 刊出日期: 2019-10-01

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

1.
Institute of Information Science and Technology, Yanshan University, Qinhuangdao 066004, China
2.
Hebei Key Laboratory of Information Transmission and Signal Processing, Qinhuangdao 066004, China

Funds: The National Natural Science Foundation of China (61471313), The Natural Science Foundation of Hebei Province (2019203318)

摘要

摘要: JPEG在高壓縮比的情況下，解壓縮后的圖像會(huì)產(chǎn)生塊效應(yīng)、邊緣振蕩效應(yīng)和模糊，嚴(yán)重影響了圖像的視覺(jué)效果。為了去除JPEG壓縮偽跡，該文提出了多尺度稠密殘差網(wǎng)絡(luò)。首先把擴(kuò)張卷積引入到殘差網(wǎng)絡(luò)的稠密塊中，利用不同的擴(kuò)張因子，使其形成多尺度稠密塊；然后采用4個(gè)多尺度稠密塊將網(wǎng)絡(luò)設(shè)計(jì)成包含2條支路的結(jié)構(gòu)，其中后一條支路用于補(bǔ)充前一條支路沒(méi)有提取到的特征；最后采用殘差學(xué)習(xí)的方法來(lái)提高網(wǎng)絡(luò)的性能。為了提高網(wǎng)絡(luò)的通用性，采用具有不同壓縮質(zhì)量因子的聯(lián)合訓(xùn)練方式對(duì)網(wǎng)絡(luò)進(jìn)行訓(xùn)練，針對(duì)不同壓縮質(zhì)量因子訓(xùn)練出一個(gè)通用模型。經(jīng)實(shí)驗(yàn)表明，該文方法不僅具有較高的JPEG壓縮偽跡去除性能，且具有較強(qiáng)的泛化能力。
- JPEG壓縮 /
- 壓縮偽跡 /
- 多尺度稠密塊 /
- 擴(kuò)張卷積
Abstract: In the case of high compression rates, the JPEG decompressed image can produce blocking artifacts, ringing effects and blurring, which affect seriously the visual effect of the image. In order to remove JPEG compression artifacts, a multi-scale dense residual network is proposed. Firstly, the proposed network introduces the dilate convolution into a dense block and uses different dilation factors to form multi-scale dense blocks. Then, the proposed network uses four multi-scale dense blocks to design the network into a structure with two branches, and the latter branch is used to supplement the features that are not extracted by the previous branch. Finally, the proposed network uses residual learning to improve network performance. In order to improve the versatility of the network, the network is trained by a joint training method with different compression quality factors, and a general model is trained for different compression quality factors. Experiments demonstrate that the proposed algorithm not only has high JPEG compression artifacts reduction performance, but also has strong generalization ability.
- JPEG compression /
- Compression artifacts /
- Multi-scale dense blocks /
- Dilate convolution

HTML全文

圖 1 多尺度稠密殘差網(wǎng)絡(luò)

下載: 全尺寸圖片幻燈片

圖 2 由擴(kuò)張因子$s = i$的擴(kuò)張卷積組成的稠密塊

下載: 全尺寸圖片幻燈片

圖 3 多尺度稠密殘差網(wǎng)絡(luò)中每個(gè)分支的輸出圖像

下載: 全尺寸圖片幻燈片

圖 4 QF為10時(shí)，圖像sailing3在各個(gè)算法中的視覺(jué)比較

下載: 全尺寸圖片幻燈片

表 1 ARCNN的4個(gè)模型在LIVE1數(shù)據(jù)集上的PSNR(dB)對(duì)比

模型	QF
模型	10	20	30	40
JPEG	27.77	30.07	31.41	32.35
ARCNN(${\rm{QF}} = 10$)	28.96	30.79	31.51	31.90
ARCNN(${\rm{QF}} = 20$)	28.78	31.30	32.53	33.30
ARCNN(${\rm{QF}} = 30$)	28.60	31.25	32.69	33.61
ARCNN(${\rm{QF}} = 40$)	28.48	31.14	32.62	33.63

下載: 導(dǎo)出CSV

表 2 本文方法在LIVE1數(shù)據(jù)集上的PSNR(dB)/SSIM對(duì)比

方法	QF
方法	10	20	30	40
JPEG	27.77/0.7905	30.07/0.8683	31.41/0.9000	32.35/0.9173
ARCNN	28.96/0.8217	31.30/0.8871	32.69/0.9161	33.63/0.9303
L4 Residual	29.08/0.8241	31.42/0.8900	32.80/0.9174	33.78/0.9322
L8 Residual	–	31.51/0.8911	–	–
DnCNN-3	29.20/0.8262	31.59/0.8936	32.98/0.9204	33.96/0.9346
本文方法	29.49/0.8329	31.81/0.8952	33.08/0.9196	34.14/0.9367

下載: 導(dǎo)出CSV

表 3 本文方法在Classic5數(shù)據(jù)集上的PSNR(dB)/SSIM對(duì)比

方法	QF
方法	10	20	30	40
JPEG	27.82/0.7800	30.12/0.8541	31.48/0.8844	32.43/0.9011
ARCNN	29.04/0.8108	31.16/0.8691	32.52/0.8963	33.34/0.9098
DnCNN-3	29.40/0.8201	31.63/0.8775	32.90/0.9011	33.77/0.9141
本文方法	29.68/0.8275	31.87/0.8798	33.03/0.9013	33.95/0.9166

下載: 導(dǎo)出CSV

表 4 本文方法在LIVE1數(shù)據(jù)集上的PSNR(dB)/SSIM對(duì)比

方法	QF
方法	15	25	35	45
JPEG	29.13/0.8402	30.81/0.8869	31.93/0.9101	32.78/0.9241
DnCNN-3	30.61/0.8697	32.35/0.9094	33.53/0.9287	34.39/0.9400
本文方法	30.83/0.8733	32.50/0.9095	33.68/0.9303	34.56/0.9416

下載: 導(dǎo)出CSV

表 5 不同尺度的選擇在LIVE1數(shù)據(jù)集上的PSNR(dB)/SSIM對(duì)比

不同尺度	QF
不同尺度	10	15	20	25
單一尺度($3 \times 3$)	29.42/0.8309	30.78/0.8719	31.75/0.8942	32.46/0.9086
單一尺度($5 \times 5$)	29.44/0.8316	30.79/0.8719	31.76/0.8945	32.46/0.9090
本文方法	29.49/0.8329	30.83/0.8733	31.81/0.8952	32.50/0.9095

下載: 導(dǎo)出CSV

表 6 不同網(wǎng)絡(luò)層數(shù)在LIVE1數(shù)據(jù)集上的PSNR(dB)/SSIM對(duì)比

不同層數(shù)	QF
不同層數(shù)	10	15	20	25
Dense3	29.45/0.8318	30.79/0.8714	31.77/0.8947	32.47/0.9090
Dense4	29.47/0.8325	30.81/0.8728	31.79/0.8950	32.49/0.9092
Dense5	29.49/0.8329	30.83/0.8733	31.81/0.8952	32.50/0.9095
Dense6	29.47/0.8324	30.81/0.8735	31.79/0.8951	32.49/0.9099

下載: 導(dǎo)出CSV

表 7 使用普通塊和稠密塊在LIVE1數(shù)據(jù)集上的PSNR(dB)/SSIM對(duì)比

方法	QF
方法	10	15	20	25
普通塊	29.39/0.8303	30.75/0.8712	31.71/0.8938	32.41/0.9081
稠密塊	29.49/0.8329	30.83/0.8733	31.81/0.8952	32.50/0.9095

下載: 導(dǎo)出CSV

參考文獻(xiàn)(20)

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

呂曉琪, 吳涼, 谷宇, 等. 基于深度卷積神經(jīng)網(wǎng)絡(luò)的低劑量CT肺部去噪[J]. 電子與信息學(xué)報(bào), 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, 張義, 等. 基于深度卷積神經(jīng)網(wǎng)絡(luò)的遙感圖像飛機(jī)目標(biāo)檢測(cè)方法[J]. 電子與信息學(xué)報(bào), 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.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問(wèn)統(tǒng)計(jì)