International Journal of Internet, Broadcasting and Communication

The Institute of Internet, Broadcasting and Communication (한국인터넷방송통신학회)
권호 표지
DOI QR코드

DOI QR Code

Demosaicing based Image Compression with Channel-wise Decoder

  • Indra Imanuel (Dept. Computer Engineering, Dongseo University) ;
  • Suk-Ho Lee (Dept. Artificial Intelligence Appliance, Dongseo University)
  • Received : 2023.08.23
  • Accepted : 2023.09.05
  • Published : 2023.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose an image compression scheme which uses a demosaicking network and a channel-wise decoder in the decoding network. For the demosaicing network, we use as the input a colored mosaiced pattern rather than the well-known Bayer pattern. The use of a colored mosaiced pattern results in the mosaiced image containing a greater amount of information pertaining to the original image. Therefore, it contributes to result in a better color reconstruction. The channel-wise decoder is composed of multiple decoders where each decoder is responsible for each channel in the color image, i.e., the R, G, and B channels. The encoder and decoder are both implemented by wavelet based auto-encoders for better performance. Experimental results verify that the separated channel-wise decoders and the colored mosaic pattern produce a better reconstructed color image than a single decoder. When combining the colored CFA with the multi-decoder, the PSNR metric exhibits an increase of over 2dB for three-times compression and approximately 0.6dB for twelve-times compression compared to the Bayer CFA with a single decoder. Therefore, the compression rate is also increased with the proposed method than with the method using a single decoder on the Bayer patterned mosaic image.

Keywords

Acknowledgement

This work was supported by the Basic Science Research Program through the National Research Foundation of Korea under Grant NRF-2022R1I1A3065211

References

  1. G. E. Hinton, R.R. Salakhutdinov, (2006) "Reducing the Dimensionality of Data with Neural Networks," Science, Vol. 313, Issue 5786, pp. 504-507, DOI:https://doi:10.1126/science.1127647
  2. P. Vincent, H. L., (2010) "Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion," Journal of Machine Learning Research, Vol. 11, pp. 3371-3408
  3. N. Japkowicz, S.J. Hanson, M.A. Gluck, (2000) "Nonlinear Autoassociation Is Not Equivalent to PCA". Neural Computation, Vol.12, No. 3, pp. 531-545, DOI:https://doi:10.1162/089976600300015691
  4. M.A. Kramer, (1991) "Nonlinear principal component analysis using autoassociative neural networks," AIChE Journal. Vol. 37, No. 2, pp. 233-243, DOI:https://doi:10.1002/aic.690370209.
  5. M. A. Kramer (1992) "Autoassociative neural networks," Computers & Chemical Engineering, Vol. 16, No. 4, pp. 313-328, DOI:https://doi:10.1016/0098-1354(92)80051-A
  6. F. Mentzer, E. Agustsson, M. Tschannen, R. Timofte, and L. Van Gool (2018) "Conditional probability models for deep image compression," arXiv:1801.04260, DOI:https://doi.org/10.48550/arXiv.1801.04260
  7. M. Li, W. Zuo, S. Gu, D. Zhao, and D. Zhang, (2017) "Learning convolutional networks for content-weighted image Compression," arXiv:1703.10553, DOI:https://doi.org/10.48550/arXiv.1703.10553
  8. H.-H. Yang and Y. Fu, "Wavelet U-Net and the Chromatic Adaptation Transform for Single Image Dehazing", in Proc. 2019 IEEE International Conference on Image Processing (ICIP), 22-25 September 2019. DOI:https://doi.org/10.1109/ICIP.2019.8803391
  9. CLIC 2022, the 5th Workshop and Challenge on Learned Image Compression, http://compression.cc/, accessed August, 10, 2022
  10. G. Toderici, D. Vincent, N. Johnston, S.J. Hwang, D. Minnen, J. Shor, M. Covell, "Full Resolution Image Compression with Recurrent Neural Networks," Proc. 2017 IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 21-26 July 2017, pp.5306-5314. DOI:https://doi.org/10.1109/CVPR.2017.577
  11. J. Balle, D. Minnen, S. Singh, S. J. Hwang, N. Johnston, "Variational image compression with a scale hyperprior," Proc. 2018 International Conference on Learning Representations(ICLR)
  12. F. Mentzer, E. Agustsson, M. Tschannen, R. Timofte, L. V. Gool, "Conditional Probability Models for Deep Image Compression," Proc. 2018 IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 18-23 June 2018, pp. 4394-4402. DOI:https://doi.org/10.1109/CVPR.2018.00462