SpringerLink
Log in

CNN with Attention-Guided Concatenation for Improved Image Restoration

  • Conference paper
  • First Online:
Artificial Intelligence Tools and Applications in Embedded and Mobile Systems (ICTA-EMOS 2022)

Part of the book series: Progress in IS ((PROIS))

  • 31 Accesses

Abstract

The performance of Deep ConNets (DCNNs) architectures has been improved in a number of ways. However, deeper Convolutional Neural Networks (CNNs) suffer from the difficulty of being trained, because widening the network introduces additional parameters and makes the denoising model more complex. Another approach is to combine image features that have been taken from various CNN architectures. In order to boost the width and, consequently, the performance of the combined network, which is better than when the networks are utilized individually, this research aims to create an improved CNN model by combining two networks. The proposed approach uses an Attention Module (ATT) at the output of the individual CNNs to select important information from the two networks before the concatenation operation. The CNN With Attention module (CWATT) performed better than the CNN with No Attention (CNOATT) on both Peak Signal to Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM).

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

Access this chapter

Log in via an institution

Institutional subscriptions

References

  1. Zha, Z., Yuan, X., Zhou, J., Zhu, C., & Wen, B. (2020). Image restoration via simultaneous nonlocal self-similarity priors. IEEE Transactions on Image Processing, 29, 8561–8576.

    Article  Google Scholar 

  2. Sun, S. (2020). Application of fuzzy image restoration in criminal investigation. Journal of Visual Communication and Image Representation, 71, 102704.

    Article  Google Scholar 

  3. Maru, M., & Parikh, M. C. (2017). Image restoration techniques: A survey. International Journal of Computer Applications, 160(6), 15–19.

    Article  Google Scholar 

  4. Farhan, R. (2020). Review on some methods used in image restoration. International Multidisciplinary Research Journal, 10, 13–16. https://doi.org/10.25081/imrj.2020.v10.6113

    Article  Google Scholar 

  5. Khare, C., & Nagwanshi, K. K. (2011). Implementation and analysis of image restoration techniques. International Journal of Computer Trends and Technology-May to June Issue, 2011(54), 1–6.

    Google Scholar 

  6. Mohammed, O. H., & Mahmood, B. S. (2021). Advance in image and audio restoration and their assessments: A Review.

    Google Scholar 

  7. Tian, C., Xu, Y., Li, Z., Zuo, W., Fei, L., & Liu, H. (2020). Attention-guided CNN for image denoising. Neural Networks, 124, 117–129.

    Article  Google Scholar 

  8. Chen, C., **ong, Z., Tian, X., & Wu, F. (2018). Deep boosting for image denoising. In Proceedings of the European conference on computer vision (ECCV) (pp. 3–18).

    Google Scholar 

  9. Tripathi, S., Lipton, Z. C., & Nguyen, T. Q., 2018. Correction by projection: Denoising images with generative adversarial networks. ar**v preprint ar**v:1803.04477.

    Google Scholar 

  10. Yue, Z., Zhao, Q., Zhang, L., & Meng, D. (2020). Dual adversarial network: Toward real-world noise removal and noise generation. In Proceedings of the European Conference on Computer Vision (ECCV) (pp. 41–58). Springer.

    Google Scholar 

  11. Tai, Y., Yang, J., Liu, X., & Xu, C. (2017). Memnet: A persistent memory network for image restoration. In Proceedings of the IEEE international conference on computer vision (pp. 4539–4547).

    Google Scholar 

  12. Zhang, Y., Tian, Y., Kong, Y., Zhong, B., & Fu, Y. (2021, July 1). Residual dense network for image restoration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(7), 2480–2495. https://doi.org/10.1109/TPAMI.2020.2968521

    Article  Google Scholar 

  13. Mao, X., Shen, C., & Yang, Y. B. (2016). Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. Advances in Neural Information Processing Systems, 29.

    Google Scholar 

  14. Liu, P., Zhang, H., Zhang, K., Lin, L., & Zuo, W. (2018). Multi-level wavelet-CNN for image restoration. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops (pp. 773–782).

    Google Scholar 

  15. Bhavani, M. D., Murugan, R., & Goel, T. (2022). Robust U-net: Development of robust image enhancement model using modified U-net architecture. Concurrency and Computation: Practice and Experience, 34(28), e7347.

    Article  Google Scholar 

  16. Zhang, K., Zuo, W., & Zhang, L. (2018). FFDNet: Toward a fast and flexible solution for CNN-based image denoising. IEEE Transactions on Image Processing, 27(9), 4608–4622.

    Article  Google Scholar 

  17. Yadav, M., & Tiwari, N. (2021). Performance Comparison of Image Restoration techniques using CNN and their applications. In 2021 5th International Conference on Computing Methodologies and Communication (ICCMC) (pp. 1146–1151). https://doi.org/10.1109/ICCMC51019.2021.9418340

    Chapter  Google Scholar 

  18. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., et al. (2015). Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1–9).

    Google Scholar 

  19. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2818–2826).

    Google Scholar 

  20. Srivastava, R. K., Greff, K., & Schmidhuber, J. (2015). Training very deep networks. Advances in Neural Information Processing Systems, 28.

    Google Scholar 

  21. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770–778).

    Google Scholar 

  22. Targ, S., Almeida, D., & Lyman, K. (2016). Resnet in resnet: Generalizing residual architectures. ar**v. https://doi.org/10.48550/ar**v.1603.08029.

  23. Lin, T. Y., Dollár, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2117–2125).

    Google Scholar 

  24. Ronneberger, O., Fischer, P., & Brox, T. (2015, October). U-net: Convolutional networks for biomedical image segmentation. In International conference on medical image computing and computer-assisted intervention (pp. 234–241). Springer.

    Google Scholar 

  25. Vo, X. T., Tran, T. D., Nguyen, D. L., & Jo, K. H. (2021, February). Stair-step feature pyramid networks for object detection. In International workshop on Frontiers of computer vision (pp. 168–175). Springer.

    Chapter  Google Scholar 

  26. Li, X., Wang, W., Hu, X., & Yang, J. (2019). Selective kernel networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 510–519).

    Google Scholar 

  27. Anwar, S., & Barnes, N. (2019). Real image denoising with feature attention. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 3155–3164).

    Google Scholar 

  28. Tian, C., Xu, Y., & Zuo, W. (2020). Image denoising using deep CNN with batch renormalization. Neural Networks, 121, 461–473.

    Article  Google Scholar 

  29. Lv, Z., Li, J., Dong, C., Li, H., & Xu, Z. (2021). Deep learning in the COVID-19 epidemic: A deep model for urban traffic revitalization index. Data & Knowledge Engineering, 135, 101912. https://doi.org/10.1016/j.datak.2021.101912

    Article  Google Scholar 

  30. Hamad, R. A., Kimura, M., Yang, L., Woo, W. L., & Wei, B. (2021). Dilated causal convolution with multi-head self attention for sensor human activity recognition. Neural Computing and Applications, 33(20), 13705–13722.

    Article  Google Scholar 

  31. Ren, W., Liu, S., Zhang, H., Pan, J., Cao, X., & Yang, M. H. (2016, October). Single image dehazing via multi-scale convolutional neural networks. In European conference on computer vision (pp. 154–169). Springer.

    Google Scholar 

  32. Reznik, Y. (2023). Another look at SSIM image quality metric. Electronic Imaging, 35(8), 305–311.

    Article  Google Scholar 

  33. Dabov, K., Foi, A., Katkovnik, V., & Egiazarian, K. (2007). Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Transactions on Image Processing, 16(8), 2080–2095.

    Article  Google Scholar 

  34. Zhang, K., Zuo, W., Chen, Y., Meng, D., & Zhang, L. (2017). Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising. IEEE Transactions on Image Processing, 26(7), 3142–3155.

    Article  Google Scholar 

  35. Michele, C. (2018). CBSD68 dataset. https://github.com/clausmichele/CBSD68-dataset/tree/master/CBSD68

  36. Franzen, R. (1999). Kodak lossless true color image suite. 4(2), 9. http://r0k.us/graphics/kodak

  37. Setiadi, D. R. I. M. (2021). PSNR vs SSIM: Imperceptibility quality assessment for image steganography. Multimedia Tools and Applications, 80(6), 8423–8444.

    Article  Google Scholar 

  38. Bhatt, R., Naik, N., & Subramanian, V. K. (2021). SSIM compliant modeling framework with denoising and deblurring applications. IEEE Transactions on Image Processing, 30, 2611–2626.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Jomo Kenyatta University of Agriculture and Technology, Nairobi, Kenya

    Gladys Mange, Ronald Waweru & Michael Kimwele

  2. University of Oldenburg, Oldenburg, Germany

    Jorge Marx Gómez

Authors
  1. Gladys Mange
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ronald Waweru
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Michael Kimwele
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jorge Marx Gómez
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. University of Oldenburg, Oldenburg, Germany

    Jorge Marx Gómez

  2. The Nelson Mandela African Institution of Science and Technology, Arusha, Tanzania

    Anael Elikana Sam

  3. The Nelson Mandela African Institution of Science and Technology, Arusha, Tanzania

    Devotha Godfrey Nyambo

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Mange, G., Waweru, R., Kimwele, M., Marx Gómez, J. (2024). CNN with Attention-Guided Concatenation for Improved Image Restoration. In: Marx Gómez, J., Elikana Sam, A., Godfrey Nyambo, D. (eds) Artificial Intelligence Tools and Applications in Embedded and Mobile Systems. ICTA-EMOS 2022. Progress in IS. Springer, Cham. https://doi.org/10.1007/978-3-031-56576-2_18

Download citation

Publish with us

Policies and ethics

Search

Navigation