Skip to main content

Convolutional Neural Network (CNN) to Reduce Construction Loss in JPEG Compression Caused by Discrete Fourier Transform (DFT)

  • 418 Accesses

Part of the Communications in Computer and Information Science book series (CCIS,volume 1946)

Abstract

In recent decades, digital image processing has gained enormous popularity. Consequently, a number of data compression strategies have been put forth, with the goal of minimizing the amount of information required to represent images. Among them, JPEG compression is one of the most popular methods that has been widely applied in multimedia and digital applications. The periodic nature of DFT makes it impossible to meet the periodic condition of an image’s opposing edges without producing severe artifacts, which lowers the image’s perceptual visual quality. On the other hand, deep learning has recently achieved outstanding results for applications like speech recognition, image reduction, and natural language processing. Convolutional Neural Networks (CNN) have received more attention than most other types of deep neural networks. The use of convolution in feature extraction results in a less redundant feature map and a smaller dataset, both of which are crucial for image compression. In this work, an effective image compression method is purposed using autoencoders. The study’s findings revealed a number of important trends that suggested better reconstruction along with good compression can be achieved using autoencoders.

Keywords

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

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   64.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   84.99
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

Learn about institutional subscriptions

Notes

  1. 1.

    Source code: https://github.com/sumn2u/neuralnetwork-jpeg.

References

  1. Rahman, M.A., Islam, S.M.S., Shin, J., Islam, M.R.: Histogram alternation based digital image compression using base-2 coding. In: 2018 Digital Image Computing: Techniques and Applications, Canberra, Australia, pp. 1–8. IEEE (2018). https://ieeexplore.ieee.org/document/8615830/

  2. Hussain, A.A., AL-Khafaji, G.K., Siddeq, M.M.: Developed JPEG algorithm applied in image compression. IOP Conf. Ser. Mater. Sci. Eng. 928(3), 032006 (2020). https://doi.org/10.1088/1757-899x/928/3/032006

  3. SMPTE: The future of the JPEG standard (2020). https://www.smpte.org/blog/the-future-of-the-jpeg-standard

  4. W3Techs: Usage statistics of image file formats for websites (2022). https://w3techs.com/technologies/overview/image_format

  5. Gonzalez, R.C., Woods, R.E., Masters, B.R.: Digital image processing (2009)

    Google Scholar 

  6. Yuan, S., Hu, J.: Research on image compression technology based on Huffman coding. J. Vis. Commun. Image Represent. 59, 33–38 (2019)

    Article  Google Scholar 

  7. Li, P., Lo, K.T.: Joint image encryption and compression schemes based on \(16 \times 16\) DCT. J. Vis. Commun. Image Represent. 58, 12–24 (2019)

    Article  Google Scholar 

  8. Rasheed, M.H., Salih, O.M., Siddeq, M.M., Rodrigues, M.A.: Image compression based on 2D Discrete Fourier Transform and matrix minimization algorithm. Array 6, 100024 (2020). https://linkinghub.elsevier.com/retrieve/pii/S2590005620300096

  9. Siddeq, M.M., Al-Khafaji, G.: Applied minimized matrix size algorithm on the transformed images by DCT and DWT used for image compression. Int. J. Comput. Appl. 70(15), 33–40 (2013)

    Google Scholar 

  10. Siddeq, M., Rodrigues, M.: A new 2D image compression technique for 3D surface reconstruction (2014)

    Google Scholar 

  11. Siddeq, M., Rodrigues, M.: A novel image compression algorithm for high resolution 3D reconstruction. 3D Res. 5(2), 7 (2014). https://doi.org/10.1007/s13319-014-0007-6

    Article  Google Scholar 

  12. Dong, Y., Jiao, W., Long, T., Liu, L., He, G.: Eliminating the effect of image border with image periodic decomposition for phase correlation based remote sensing image registration. Sensors 19(10), 2329 (2019). https://www.mdpi.com/1424-8220/19/10/2329

  13. Leprince, S., Barbot, S., Ayoub, F., Avouac, J.P.: Automatic and precise orthorectification, coregistration, and subpixel correlation of satellite images, application to ground deformation measurements. IEEE Trans. Geosci. Remote Sens. 45(6), 1529–1558 (2007)

    Article  Google Scholar 

  14. Podder, P., Khan, T.Z., Khan, M.H., Rahman, M.M.: Comparative performance analysis of hamming, hanning and blackman window. Int. J. Comput. Appl. 96(18), 1–7 (2014). http://research.ijcaonline.org/volume96/number18/pxc3896927.pdf

  15. Ge, P., Lan, C., Wang, H.: An improvement of image registration based on phase correlation. Optik 125(22), 6709–6712 (2014). https://www.sciencedirect.com/science/article/pii/S0030402614010377

  16. Pouyanfar, S., et al.: A survey on deep learning: algorithms, techniques, and applications. ACM Comput. Surv. 51(5), 1–36 (2019). https://doi.org/10.1145/3234150

    Article  Google Scholar 

  17. Li, J., Wang, Y., Xie, H., Ma, K.K.: Learning a single model with a wide range of quality factors for JPEG image artifacts removal. IEEE Trans. Image Process. 29, 8842–8854 (2020). https://doi.org/10.1109/TIP.2020.3020389

    Article  MATH  Google Scholar 

  18. Svoboda, P., Hradis, M., Barina, D., Zemcik, P.: Compression artifacts removal using convolutional neural networks. arXiv:1605.00366 [cs] (2016). http://arxiv.org/abs/1605.00366

  19. Baig, M.H., Koltun, V., Torresani, L.: Learning to inpaint for image compression. arXiv:1709.08855 [cs] (2017). http://arxiv.org/abs/1709.08855

  20. Santurkar, S., Budden, D., Shavit, N.: Generative compression. arXiv:1703.01467 [cs] (2017). http://arxiv.org/abs/1703.01467

  21. Pielawski, N., Wählby, C.: Introducing Hann windows for reducing edge-effects in patch-based image segmentation. PLoS ONE 15(3), e0229839 (2020). https://doi.org/10.1371/journal.pone.0229839

    Article  Google Scholar 

  22. Cheng, Z., Sun, H., Takeuchi, M., Katto, J.: Deep convolutional autoencoder-based lossy image compression. In: 2018 Picture Coding Symposium (PCS), pp. 253–257 (2018)

    Google Scholar 

  23. Alexandre, D., Chang, C.P., Peng, W.H., Hang, H.M.: An autoencoder-based learned image compressor: description of challenge proposal by NCTU (2019). https://arxiv.org/abs/1902.07385

  24. Santurkar, S., Tsipras, D., Ilyas, A., Madry, A.: How does batch normalization help optimization? (2018). https://arxiv.org/abs/1805.11604

  25. Audhkhasi, K., Osoba, O., Kosko, B.: Noise-enhanced convolutional neural networks. Neural Netw. 78, 15–23 (2016). https://linkinghub.elsevier.com/retrieve/pii/S0893608015001896

  26. Gustineli, M.: A survey on recently proposed activation functions for deep learning (2022). https://arxiv.org/abs/2204.02921

  27. Dubey, S.R., Singh, S.K., Chaudhuri, B.B.: Activation functions in deep learning: a comprehensive survey and benchmark (2021). https://arxiv.org/abs/2109.14545

  28. Kundu, S., Mostafa, H., Sridhar, S.N., Sundaresan, S.: Attention-based image upsampling (2020). https://arxiv.org/abs/2012.09904

  29. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2014). https://arxiv.org/abs/1412.6980

  30. Shorten, C., Khoshgoftaar, T.M.: A survey on Image Data Augmentation for Deep Learning. Journal of Big Data 6(1), 60 (Dec 2019), https://journalofbigdata.springeropen.com/articles/10.1186/s40537-019-0197-0

  31. Gupta, B.C.: Sampling methods, pp. 89–121 (2021)

    Google Scholar 

  32. Yadav, S., Shukla, S.: Analysis of k-fold cross-validation over hold-out validation on colossal datasets for quality classification. In: 2016 IEEE 6th International Conference on Advanced Computing (IACC), pp. 78–83 (2016)

    Google Scholar 

  33. Hui, L., Belkin, M.: Evaluation of neural architectures trained with square loss vs cross-entropy in classification tasks (2020). https://arxiv.org/abs/2006.07322

  34. Steck, H., Garcia, D.G.: On the regularization of autoencoders (2021). https://arxiv.org/abs/2110.11402

  35. Ede, J.M., Beanland, R.: Adaptive learning rate clipping stabilizes learning. Mach. Learn. Sci. Technol. 1(1), 015011 (2020). https://doi.org/10.1088/2632-2153/ab81e2

    Article  Google Scholar 

  36. Rice, L., Wong, E., Kolter, J.Z.: Overfitting in adversarially robust deep learning (2020). https://arxiv.org/abs/2002.11569

  37. Deshmukh, K.R.: Image compression using neural networks. Master of science, San Jose State University, San Jose, CA, USA (2019). https://scholarworks.sjsu.edu/etd_projects/666

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Suman Kunwar .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Kunwar, S. (2024). Convolutional Neural Network (CNN) to Reduce Construction Loss in JPEG Compression Caused by Discrete Fourier Transform (DFT). In: Zhao, F., Miao, D. (eds) AI-generated Content. AIGC 2023. Communications in Computer and Information Science, vol 1946. Springer, Singapore. https://doi.org/10.1007/978-981-99-7587-7_25

Download citation

  • DOI: https://doi.org/10.1007/978-981-99-7587-7_25

  • Published:

  • Publisher Name: Springer, Singapore

  • Print ISBN: 978-981-99-7586-0

  • Online ISBN: 978-981-99-7587-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics