Advertisement

Demosaicing Using MFIT (Matrix Factorization Iterative Tunable) Based on Convolution Neural Network

  • Shabana TabassumEmail author
  • SanjayKumar C. Gowre
Conference paper
Part of the Lecture Notes on Data Engineering and Communications Technologies book series (LNDECT, volume 38)

Abstract

Demosaicing is introduced for estimation of the other missing color for producing the absolute color image. Enormous research has been done in past to develop the Demosaicing algorithm, however all these methods have shortcomings, hence in this paper, we propose an algorithm called MF-IT (Matrix Factorization Iterative Tunable), this methodology is based on the CNN (Convolution Neural Network), the main aim of this research is to improvise the reconstruction quality of the given image. This is achieved by using the image-block adjustments based transform, which helps in utilizing the image block based transform. One of the main advantage of MFIT is shift invariance, which can be easily obtained without any support of striding image blocks. Henceforth, In order to evaluate the performance of our methodology it is compared against the various state-of-art method. The result analysis shows that proposed methodology simply outperforms the other method.

Keywords

Demosaicing Image block Stride Non-stride 

References

  1. 1.
    Gamal, E., Eltoukhy, H.: CMOS image sensors. IEEE Circ. Dev. Mag. 21(3), 6–20 (2005)CrossRefGoogle Scholar
  2. 2.
    Moghavvemi, M., Jamuar, S.S., Gan, E.H., Yap, Y.C.: Design of low cost flexible RGB color sensor. In: 2012 International Conference on Informatics, Electronics & Vision (ICIEV), Dhaka, pp. 1158–1162 (2012)Google Scholar
  3. 3.
    Lukac, R., Plataniotis, K.N.: Color filter arrays: design and performance analysis. IEEE Trans. Consum. Electron. 51(4), 1260–1267 (2005)CrossRefGoogle Scholar
  4. 4.
    Zhang, C., Li, Y., Wang, J., Hao, P.: Universal demosaicing of color filter arrays. IEEE Trans. Image Process. 25(11), 5173–5186 (2016)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Gunturk, B.K., Glotzbach, J., Altunbasak, Y., Schafer, R.W., Mersereau, R.M.: Demosaicing: color filter array interpolation. IEEE Signal Process. Mag. 22(1), 44–54 (2005)CrossRefGoogle Scholar
  6. 6.
    Mairal, J., Elad, M., Sapiro, G.: Sparse representation for color image restoration. IEEE Trans. Image Process. 17(1), 53–69 (2008)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Mairal, J., Bach, F., Ponce, J., Sapiro, G., Zisserman, A.: Non-local sparse models for image restoration. In: Proceedings of IEEE ICCV 2009, pp. 2272–2279 (2009)Google Scholar
  8. 8.
    Monno, Y., Kiku, D., Tanaka, M., Okutomi, M.: Adaptive residual interpolation for color image demosaicing. In: Proceedings of IEEE ICIP 2015, pp. 3861–3865 (2015)Google Scholar
  9. 9.
    Bayer, B.E.: Color imaging array. U.S. Patent 3971065, 20 July 1976Google Scholar
  10. 10.
    Wang, J., Zhang, C., Hao, P.: New color filter arrays of high light sensitivity and high demosaicing performance. In: Proceedings of the 18th IEEE International Conference on Image Processing (ICIP), pp. 3153–3156, September 2011Google Scholar
  11. 11.
    Taubman, D.: Generalized Wiener reconstruction of images from colour sensor data using a scale invariant prior. In: Proceedings of the International Conference on Image Processing (ICIP), vol. 3, pp. 801–804 (2000)Google Scholar
  12. 12.
    Alleysson, D., Susstrunk, S., Hérault, J.: Linear demosaicing inspired by the human visual system. IEEE Trans. Image Process. 14(4), 439–449 (2005)CrossRefGoogle Scholar
  13. 13.
    Hirakawa, K., Wolfe, P.J.: Spatio-spectral color filter array design for optimal image recovery. IEEE Trans. Image Process. 17(10), 1876–1890 (2008)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Gharbi, M., Chaurasia, G., Paris, S., Durand, F.: Deep joint demosaicing and denoising. ACM Trans. Graph. 35(6), 191:1–191:12 (2016)CrossRefGoogle Scholar
  15. 15.
    Tan, R., Zhang, K., Zuo, W., Zhang, L.: Color image demosaicing via deep residual learning. In: Proceedings of IEEE ICME 2017 (2017)Google Scholar
  16. 16.
    Zhang, L., Wu, X.: Color demosaicing via directional linear minimum mean square-error estimation. IEEE Trans. Image Process. 14(12), 2167–2178 (2005)CrossRefGoogle Scholar
  17. 17.
    Pekkucuksen, I., Altunbasak, Y.: Gradient based threshold free color filter array interpolation. In: Proceedings of the International Conference on Image Processing, ICIP, 26–29 September 2010, pp. 137–140 (2010)Google Scholar
  18. 18.
    Mairal, J., Bach, F.R., Ponce, J., Sapiro, G., Zisserman, A.: Nonlocal sparse models for image restoration. In: IEEE 12th International Conference on Computer Vision, ICCV, 27 September–4 October 2009, pp. 2272–2279 (2009)Google Scholar
  19. 19.
    Zhang, L., Wu, X., Buades, A., Li, X.: Color demosaicing by local directional interpolation and nonlocal adaptive thresholding. J. Electron. Imaging 20(2), 023016 (2011)CrossRefGoogle Scholar
  20. 20.
    Lu, Y.M., Karzand, M., Vetterli, M.: Demosaicing by alternating projections: theory and fast one-step implementation. IEEE Trans. Image Process. 19(8), 2085–2098 (2010)MathSciNetCrossRefGoogle Scholar
  21. 21.
    Wang, Y.: A multilayer neural network for image demosaicing. In: IEEE International Conference on Image Processing, ICIP, 27–30 October 2014, pp. 1852–1856 (2014)Google Scholar
  22. 22.
    Duran, J., Buades, A.: A demosaicing algorithm with adaptive interchannel correlation. IPOL J. 5, 311–327 (2015)CrossRefGoogle Scholar
  23. 23.
    Gharbi, M., Chaurasia, G., Paris, S., Durand, F.: Deep joint demosaicing and denoising. ACM Trans. Graph. 35(6), 191 (2016)CrossRefGoogle Scholar
  24. 24.
    Beyond color difference: residual interpolation for color image demosaicing. IEEE Trans. Image Process. 25(3), 1288–1300 (2016)Google Scholar
  25. 25.
    Wu, J., Timofte, R., Gool, L.J.V.: Demosaicing based on directional difference regression and efficient regression priors. IEEE Trans. Image Process. 25(8), 3862–3874 (2016)MathSciNetCrossRefGoogle Scholar
  26. 26.
    Hua, K., Hidayati, S.C., He, F., Wei, C., Wang, Y.F.: Contextaware joint dictionary learning for color image demosaicing. J. Vis. Commun. Image Represent. 38, 230–245 (2016)CrossRefGoogle Scholar
  27. 27.
    Tan, D.S., Chen, W., Hua, K.: Deep demosaicing: adaptive image demosaicing via multiple deep fully convolutional networks. IEEE Trans. Image Process. 27(5), 2408–2419 (2018)MathSciNetCrossRefGoogle Scholar
  28. 28.
    Luong, H.Q., Goossens, B., Aelterman, J., Pižurica, A., Philips, W.: A primal-dual algorithm for joint demosaicing and deconvolution. In: 2012 19th IEEE International Conference on Image Processing, Orlando, FL, pp. 2801–2804 (2012)Google Scholar
  29. 29.
    Liu, H., Liu, D., Mansour, H., Boufounos, P.T., Waller, L., Kamilov, U.S.: SEAGLE: sparsity-driven image reconstruction under multiple scattering. IEEE Trans. Comput. Imaging 4(1), 73–86 (2018)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Department of E&CEKBN College of EngineeringKalaburagiIndia
  2. 2.Department of E&CEBKITBhalkiIndia

Personalised recommendations