Supervised-learning-based algorithm for color image compression

  • Liu, Xue-Dong (Key Laboratory of Broadband Wireless Communications and Sensor Networks, School of Information Engineering, Wuhan University of Technology) ;
  • Wang, Meng-Yue (Key Laboratory of Broadband Wireless Communications and Sensor Networks, School of Information Engineering, Wuhan University of Technology) ;
  • Sa, Ji-Ming (Key Laboratory of Broadband Wireless Communications and Sensor Networks, School of Information Engineering, Wuhan University of Technology)
  • Received : 2018.10.09
  • Accepted : 2019.07.29
  • Published : 2020.04.03


A correlation exists between luminance samples and chrominance samples of a color image. It is beneficial to exploit such interchannel redundancy for color image compression. We propose an algorithm that predicts chrominance components Cb and Cr from the luminance component Y. The prediction model is trained by supervised learning with Laplacian-regularized least squares to minimize the total prediction error. Kernel principal component analysis mapping, which reduces computational complexity, is implemented on the same point set at both the encoder and decoder to ensure that predictions are identical at both the ends without signaling extra location information. In addition, chrominance subsampling and entropy coding for model parameters are adopted to further reduce the bit rate. Finally, luminance information and model parameters are stored for image reconstruction. Experimental results show the performance superiority of the proposed algorithm over its predecessor and JPEG, and even over JPEG-XR. The compensation version with the chrominance difference of the proposed algorithm performs close to and even better than JPEG2000 in some cases.


  1. JPEG Std. ISO/IEC 10918 - 1 and ITU - T.81, Information Technology: Digital Compression and Coding of Continuous -Tone Still Images: Requirements and Guidelines, 1993.
  2. M. Charrier, D. S. Cruz, and M. Larsson, JPEG2000, the next millennium compression standard for still images, in Proc. Int. Conf. Multimedia Comput. Syst., Florence, Italy, June 1999, pp. 131-132.
  3. F. Dufaux, G. J. Sullivan, and T. Ebrahimi, The JPEG XR image coding standard [Standards in a Nutshell], IEEE Signal Process. Mag., 26 (2009), no. 6, 195-199 and 204.
  4. K. R. Rao, J. J. Hwang, and D. N. Kim, High Efficiency Video Coding and Other Emerging Standards, River Publishers, Aalborg, Denmark, 2017.
  5. X. Zhang, F. Zou, and O. C. Au, Chrominance intra-prediction based on inter-channel correlation for HEVC, IEEE Trans. Image Process. 23 (2014), no. 1, 274-286.
  6. K. Zhang et al., Enhanced cross-component linear model for chroma intra-prediction in video coding, IEEE Trans. Image Process. 27 (2018), no. 8, 3983-3997.
  7. S. Lee et al., Colorization-based compression using optimization, IEEE Trans. Image Process. 22 (2013), no. 7, 2627-2636.
  8. K. Uruma et al., Colorization-based image coding using graph Fourier transform, Signal Process.: Image Com. 74 (2019), 266-279.
  9. L. Cheng and S. V. N. Vishwanathan, Learning to compress images and videos, in Proc. Mach. Learn., Corvallis, OR, USA, June 2007, pp. 161-168.
  10. A. Atkinson, A. Donev, and R. Tobias, Optimum Experimental Designs With SAS (Series Oxford Statistical Science), Oxford Univ. Press, Oxford, U.K., 2007, pp. 151-153.
  11. X. He, M. Ji, and H. Bao, A unified active and semi-supervised learning framework for image compression, in Proc. IEEE Conf. CVPR, Miami, FL, USA, June 2009, pp. 65-72.
  12. C. Zhang and X. He, Image compression by learning to minimize the total error, IEEE Trans. Circuits Syst. Video Technol. 23 (2013), no. 4, 565-576.
  13. M. Belkin, P. Niyogi, and V. Sindhwani, Manifold regularization: A geometric framework for learning from labeled and unlabeled examples, J. Mach. Learn. 7 (2006), 2399-2434.
  14. X. Liu and J. Yang, Fast and high efficient color image compression using machine learning, in Proc. IEEE Adv. Inf. Manag. Commun. Electron. Autom. Contr. Conf., Xi'an, China, May 2018, pp. 470-473.
  15. B. Scholkopf and A. J. Smola, Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond, MIT Press, Cambridge, MA, 2001.
  16. F. R. K. Chung, Spectral Graph Theory, Am. Math. Soc., Providence, RI, 1997.
  17. J. Shi and J. Malik, Normalized cuts and image segmentation, IEEE Trans. Patt. Anal. Mach. Intell. 22 (2000), no. 8, 888-905.
  18. Z. Wang et al., Image quality assessment: From error visibility to structural similarity, IEEE Trans. Image Process. 13 (2004), no. 4, 600-612.
  19. G. A. F. Seber, A Matrix Handbook for Statisticians (Wiley Series in Probability and Mathematical Statistics), Wiley, Hoboken, NJ, USA, 2008.
  20. CodePlex Archive, Open source implementation of jpegxr, Available from
  21. G. Bjontegaard, Calculation of Average PSNR Differences Between RD Curves, Document VCEG‐M33, ITU‐T Q6/16, Austin, TX, USA, 2001.
  22. A. Rahimi and B. Recht. Random features for large-scale kernel machines, in Proc. Int. Conf. Neural Inf. Process. Syst., Vancouver, Canada, Dec. 2008, pp. 1177-1184.