Skip to main content
SpringerLink
Log in

The Concatenated Dynamic Convolutional and Sparse Coding on Image Artifacts Reduction

  • Conference paper
  • First Online:
Computational Science and Its Applications – ICCSA 2021 (ICCSA 2021)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 12950))

Included in the following conference series:

  • 1436 Accesses

Abstract

In order to enhance compressed JPEG image, a deep convolutional sparse coding network is proposed in this article. The network integrates state-of-the-art dynamic convolution to extract multi-scale image features, and uses convolutional sparse coding to separate image artifacts to generate coded feature for the final image reconstruction. Since this architecture consolidates model-based convolutional sparse coding with deep neural network, that allow this method has more interpretability. Also, compared with the existing network, which uses a dilated convolution as a feature extraction approach, this proposed concatenated dynamic method has improved de-blocking result in both numerical experiments and visual effect. Besides, in the higher compressed quality task, the proposed model has more pronounced improvement in reconstructed image quality evaluations.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Ahmed, N., Natarajan, T., Rao, K.: Discrete cosine transform. IEEE Trans. Comput. C-23, 90–93 (1974)

    Google Scholar 

  2. Arbeláez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 33, 898–916 (2011)

    Article  Google Scholar 

  3. Chen, Y., Dai, X., Liu, M., Chen, D., Yuan, L., Liu, Z.: Dynamic convolution: attention over convolution kernels. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition on Proceedings, pp. 11030–11039 (2020)

    Google Scholar 

  4. Chen, Y., Pock, T.: Trainable nonlinear reaction diffusion: a flexible framework for fast and effective image restoration. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1256–1272 (2017)

    Article  Google Scholar 

  5. Chung-Bin, W., Bin-Da, L., Jar-Ferr, Y.: Adaptive postprocessors with DCT-based block classifications. IEEE Trans. Circuits Syst. Video Technol. 13, 365–375 (2003)

    Article  Google Scholar 

  6. Connell, J.: A Huffman-Shannon-Fano code. Proc. IEEE 61, 1046–1047 (1973)

    Article  Google Scholar 

  7. Dong, C., Deng, Y., Loy, C. C., Tang, X.: Compression artifacts reduction by a deep convolutional network. In: IEEE International Conference on Computer Vision on Proceedings, pp. 576–584 (2015)

    Google Scholar 

  8. Dong, C., Loy, C.C., He, K., Tang, X.: Learning a deep convolutional network for image super-resolution. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 184–199. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10593-2_13

    Chapter  Google Scholar 

  9. Dyer, E.L., Johnson, D.H., Baraniuk, R.G.: Learning modular representations from global sparse coding networks. BMC Neurosci. 11, P131 (2010). https://doi.org/10.1186/1471-2202-11-S1-P131

  10. Foi, A., Katkovnik, V., Egiazarian, K.: Pointwise shape-adaptive DCT for high-quality denoising and deblocking of grayscale and color images. IEEE Trans. Image Process. 16, 1395–1411 (2007)

    Article  MathSciNet  Google Scholar 

  11. Fu, X., Zha, Z.J., Wu, F., Ding, X., Paisley, J.: Jpeg artifacts reduction via deep convolutional sparse coding. In: IEEE/CVF International Conference on Computer Vision on Proceedings, pp. 2501–2510 (2019)

    Google Scholar 

  12. Galteri, L., Seidenari, L., Bertini, M., Bimbo, A.: Deep universal generative adversarial compression artifact removal. IEEE Trans. Multimedia 21, 2131–2145 (2019)

    Article  Google Scholar 

  13. Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition on Proceedings, pp. 2414–2423 (2016)

    Google Scholar 

  14. Guangtao, Z., Wenjun, Z., Xiaokang, Y., Weisi, L., Yi, X.: Efficient deblocking with coefficient regularization, shape-adaptive filtering, and quantization constraint. IEEE Trans. Multimedia 10, 735–745 (2008)

    Article  Google Scholar 

  15. Hannuksela, M., Lainema, J., Malamal Vadakital, V.: The high efficiency image file format standard [Standards in a Nutshell]. IEEE Signal Process. Mag. 32, 150–156 (2015)

    Article  Google Scholar 

  16. Heide, F., Heidrich, W., Wetzstein, G.: Fast and flexible convolutional sparse coding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition on Proceedings, pp. 5135–5143 (2015)

    Google Scholar 

  17. Hinds, S., Fisher, J., D’Amato, D.: A document skew detection method using run-length encoding and the Hough transform. In: Proceedings. 10th International Conference on Pattern Recognition (1990)

    Google Scholar 

  18. Howard, P., Vitter, J.: Fast and efficient lossless image compression. In: Proceedings DCC 1993: Data Compression Conference (1993)

    Google Scholar 

  19. Hu, J., Shen, L., Albanie, S., Sun, G., Wu, E.: Squeeze-and-excitation networks. IEEE Trans. Pattern Anal. Mach. Intell. 42, 2011–2023 (2020)

    Article  Google Scholar 

  20. Huynh-Thu, Q., Ghanbari, M.: Scope of validity of PSNR in image/video quality assessment. Electron. Lett. 44, 800 (2008)

    Article  Google Scholar 

  21. JPEG - JPEG. https://jpeg.org/jpeg/. Accessed 26 Nov 2020

  22. Khayam, S.A.: The discrete cosine transform (DCT): theory and application. Mich. State Univ. 114, 1–31 (2003)

    Google Scholar 

  23. Knuth, D.: Dynamic huffman coding. J. Algorithms 6, 163–180 (1985)

    Article  MathSciNet  Google Scholar 

  24. Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60, 84–90 (2017)

    Article  Google Scholar 

  25. Li, Yu., Guo, F., Tan, R.T., Brown, M.S.: A contrast enhancement framework with JPEG artifacts suppression. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8690, pp. 174–188. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10605-2_12

    Chapter  Google Scholar 

  26. List, P., Joch, A., Lainema, J., Bjontegaard, G., Karczewicz, M.: Adaptive deblocking filter. IEEE Trans. Circuits Syst. Video Technol. 13, 614–619 (2003)

    Article  Google Scholar 

  27. Liu, X., Wu, X., Zhou, J., Zhao, D.: Data-driven soft decoding of compressed images in dual transform-pixel domain. IEEE Trans. Image Process. 25, 1649–1659 (2016)

    Article  MathSciNet  Google Scholar 

  28. Nagy, J., O’Leary, D.: Restoring images degraded by spatially variant blur. SIAM J. Sci. Comput. 19, 1063–1082 (1998)

    Article  MathSciNet  Google Scholar 

  29. Redmill, D., Kingsbury, N.: The EREC: an error-resilient technique for coding variable-length blocks of data. IEEE Trans. Image Process. 5, 565–574 (1996)

    Article  Google Scholar 

  30. Rudin, L., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Phys. D: Nonlinear Phenomena 60, 259–268 (1992)

    Article  MathSciNet  Google Scholar 

  31. Rothe, R., Timofte, R., Van Gool, L.: Efficient regression priors for reducing image compression artifacts. In: 2015 IEEE International Conference on Image Processing (ICIP) (2015)

    Google Scholar 

  32. Tai, Y., Yang, J., Liu, X., Xu, C.: Memnet: a persistent memory network for image restoration. In: IEEE International Conference on Computer Vision on Proceedings, pp. 4539–4547 (2017)

    Google Scholar 

  33. Tuchler, M., Singer, A., Koetter, R.: Minimum mean squared error equalization using a priori information. IEEE Trans. Signal Process. 50, 673–683 (2002)

    Article  Google Scholar 

  34. Usevitch, B.: A tutorial on modern lossy wavelet image compression: foundations of JPEG 2000. IEEE Signal Process. Mag. 18, 22–35 (2001)

    Article  Google Scholar 

  35. Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13, 600–612 (2004)

    Article  Google Scholar 

  36. Wang, Z., Liu, D., Chang, S., Ling, Q., Yang, Y., Huang, T.S.: D3: deep dual-domain based fast restoration of JPEG-compressed images. In: IEEE Conference on Computer Vision and Pattern Recognition on Proceedings, pp. 2764–2772 (2016)

    Google Scholar 

  37. Yu, F. and Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)

  38. Zhang, K., Zuo, W., Chen, Y., Meng, D., Zhang, L.: Beyond a gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Trans. Image Process. 26, 3142–3155 (2017)

    Article  MathSciNet  Google Scholar 

  39. Zhang, X., Yang, W., Hu, Y., Liu, J.: DMCNN: dual-domain multi-scale convolutional neural network for compression artifacts removal. In: 2018 25th IEEE International Conference on Image Processing (ICIP), pp. 390–394. IEEE (2018)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Norwegian University of Science and Technology, Gjøvik, Norway

    Linna Yang & Ronny Velastegui

Authors
  1. Linna Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ronny Velastegui
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Linna Yang .

Editor information

Editors and Affiliations

  1. University of Perugia, Perugia, Italy

    Osvaldo Gervasi

  2. University of Basilicata, Potenza, Potenza, Italy

    Beniamino Murgante

  3. Covenant University, Ota, Nigeria

    Sanjay Misra

  4. University of Cagliari, Cagliari, Italy

    Chiara Garau

  5. University of Cagliari, Cagliari, Italy

    Ivan Blečić

  6. Monash University, Clayton, VIC, Australia

    David Taniar

  7. Kyushu Sangyo University, Fukuoka, Japan

    Bernady O. Apduhan

  8. University of Minho, Braga, Portugal

    Ana Maria A.C. Rocha

  9. Polytechnic University of Bari, Bari, Italy

    Eufemia Tarantino

  10. Polytechnic University of Bari, Bari, Italy

    Carmelo Maria Torre

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Yang, L., Velastegui, R. (2021). The Concatenated Dynamic Convolutional and Sparse Coding on Image Artifacts Reduction. In: Gervasi, O., et al. Computational Science and Its Applications – ICCSA 2021. ICCSA 2021. Lecture Notes in Computer Science(), vol 12950. Springer, Cham. https://doi.org/10.1007/978-3-030-86960-1_8

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-86960-1_8

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-86959-5

  • Online ISBN: 978-3-030-86960-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation