Research on Color Space Conversion Model from CMYK to CIE-LAB Based on GRNN

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10749)


In order to reproduce color information accurately in cross media transmission, a color space conversion model from CMYK color space to CIE-LAB based on generalized regression neural network (GRNN) was proposed. According to the structure and mathematical model of GRNN neural network, the CMYK-LAB color space conversion model was established. By training sample and comparing the mean square error of the sample data, the distribution coefficients were determined, and CMYK- LAB color space conversion model based on GRNN was eventually obtained and the accuracy was tested. According to these data, sample data and test data was determined. The results showed that color space conversion from CMYK to CIE-LAB on GRNN had faster conversion speed and accuracy compared with the color space conversion method based on BP neural network, the demand on printing industry can be met.


Color space conversion Generalized regression neural network CMYK CIE-LAB BP neural network 



This work is supported by the Natural Science Fund for Colleges and Universities of Anhui Province (No. KJ2017ZD32) and the Innovation Fund for graduate students of Huaibei Normal University.


  1. 1.
    McCulloch, W., Pitts, W.: Logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys. 5, 115–133 (1943)MathSciNetCrossRefMATHGoogle Scholar
  2. 2.
    Hansen, J.V., Meservy, R.D.: Learning experiments with genetic optimization of a generalized regression neural network. Decis. Support Syst. 18(3–4), 317–325 (1996)CrossRefGoogle Scholar
  3. 3.
    Anwar, T., Aung, Y.M., Jumaily, A.A.: The estimation of knee joint angle based on generalized regression neural network (GRNN). In: IEEE International Symposium on Robotics and Intelligent Sensors, pp. 208–213 (2016)Google Scholar
  4. 4.
    Alilou, V.K., Yaghmaee, F.: Application of GRNN neural network in non-texture image inpainting and restoration. Pattern Recogn. Lett. 62(C), 24–31 (2015)CrossRefGoogle Scholar
  5. 5.
    Kendrick, R.L., Acton, D.S., Duncan, A.L.: Phase-diversity wave-front sensor for imaging systems. Appl. Opt. 33(27), 6533–6546 (1994)CrossRefGoogle Scholar
  6. 6.
    Ben-Nakhi, A.E., Mahmoud, M.A.: Energy conservation in buildings through efficient A/C control using neural networks. Appl. Energy 73(1), 5–23 (2002)CrossRefGoogle Scholar
  7. 7.
    Osmak, S., Gosak, D., Glasnovic, A.: Dynamic mathematical model of deep bed filtration process. Comput. Chem. Eng. 21(10), S763–S768 (1997)CrossRefGoogle Scholar
  8. 8.
    Chen, Z.H., Wang, Z.Z., Sheng, B.: Dynamic RGB-to-CMYK conversion using visual contrast optimization. IET Image Process. 11(7), 539–549 (2017)CrossRefGoogle Scholar
  9. 9.
    Sharma, A., Gouch, M.P., Rughani, D.N.: Generation of an ICC profile from a proprietary style file. J. Imaging. Sci. 46(1), 26–32 (2002)Google Scholar
  10. 10.
    Hu, J.L., Deng, J.B., Sui, M.X.: Color space conversion model from CMYK to CIE-LAB based on prism. In: International Conference on Granular Computing, pp. 235–238 (2009)Google Scholar
  11. 11.
    Hu, J., Deng, J., Zou, S.: A novel algorithm for color space conversion model from CMYK to CIE-LAB. J. Multimed. 5(2), 159–166 (2010)CrossRefGoogle Scholar
  12. 12.
    Cao, C.J., Liu, Q.J.: Study on color space conversion based on RBF neural network. J. Adv. Mater. Res. 174, 28–31 (2011)CrossRefGoogle Scholar
  13. 13.
    Cao, C., Jing, S.: Study on color space conversion between CMYK and CIE L*a*b* based on generalized regression neural network. In: International Conference on Computer Science and Software Engineering, pp. 275–277 (2008)Google Scholar
  14. 14.
    Specht, D.F.: A general regression neural network. IEEE Trans. Neural Netw. 2(6), 568 (1991)CrossRefGoogle Scholar
  15. 15.
    Hoti, F.: On estimation of a probability density function and mode. Ann. Math. Stat. 33(3), 1065–1076 (2003)MathSciNetGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.College of Computer Science and TechnologyHuaibei Normal UniversityAnhuiChina

Personalised recommendations