Hardware and Software Complex for Automatic Level Estimation and Removal of Gaussian Noise in Images

  • Serhiy V. Balovsyak
  • Khrystyna S. Odaiska
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 754)


The hardware and software complex for an automatic level estimation and the removal of Gaussian noise in digital images has been developed. The complex consists of video cameras, computers and the software developed in MATLAB.

The calculation of Gaussian noise level is performed by the developed method, which is based on image filtering and iterative selection of region of interest. As the noise level, its standard deviation is considered. The developed software is designed for the video camera adjustment and is aimed at obtaining a series of images of one object, taken with video camera under the same lighting conditions, but at different values of the brightness parameter. For each image from the series, calculation of noise level and signal-to-noise ratio enable one to determine the optimal value of the brightness parameter.

The mathematical model, the method and the software for automatic removal of Gaussian noise in digital images with the use quasi-optimal Gaussian filter have been developed. A signal is described by the sum of the sinusoids, the amplitudes and periods of which are calculated on the basis of the energy spectrum of the original image. The quasi-optimal value of the standard deviation of the Gaussian filter kernel is obtained as the value at which the standard deviation between the filtered image brightness and the signal brightness is minimized. The accuracy of the developed filtration method has been verified by removing Gaussian noise in a set of 100 test images.


Video camera Digital image processing Gaussian noise Gaussian filter Automatic image filtering 


  1. 1.
    Bovik, A.L.: The Essential Guide to Image Processing. Elsevier Inc, Burlington (2009)CrossRefGoogle Scholar
  2. 2.
    Gonzalez, R., Woods, R.: Digital Image Processing. Prentice Hall, Upper Saddle River (2002)Google Scholar
  3. 3.
    Gonzalez, R., Woods, R., Eddins, L.: Digital Image Processing using MATLAB. Prentice Hall, Upper Saddle River (2004)Google Scholar
  4. 4.
    Liu, X., Tanaka, M., Okutomi, M.: Single-image noise level estimation for blind denoising. IEEE Trans. Image Process. 22(12), 5226–5237 (2013)CrossRefGoogle Scholar
  5. 5.
    Zoran, D., Weiss, Y.: Scale invariance and noise in natural images. In: Proceedings of the IEEE 12th International Conference on Computer Vision, pp. 2209–221 (2009)Google Scholar
  6. 6.
    Balovsyak, S.V., Odaiska, K.S.: Automatic highly accurate estimation of Gaussian noise level in digital images using filtration and edges detection methods. Int. J. Image, Graph. Sig. Process. (IJIGSP) 9(12), 1–11 (2017). Scholar
  7. 7.
    Russ, J.C.: The Image Processing Handbook. Taylor and Francis Group, Boca Raton (2011)Google Scholar
  8. 8.
    Liu, C., Szeliski, R., Kang, S.B., Zitnick, C.L., Freeman, W.T.: Automatic estimation and removal of noise from a single image. IEEE Trans. Pattern Anal. Mach. Intell. 30(2), 299–314 (2008)CrossRefGoogle Scholar
  9. 9.
    Tsin, Y., Ramesh, V., Kanade, T.: Statistical calibration of CCD imaging process. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 480–487 (2001)Google Scholar
  10. 10.
    Balovsyak, S.V., Odaiska, K.S.: Automatic removal of Gaussian noise in Digital images by Quasi-optimal Gauss Filter. Radioelectron. Comput. Syst. 83(3). 26–35 (2017). (in Ukrainian).
  11. 11.
    Solonyna, A.Y., Ulakhovych, D.A., Arbuzov, S.M., Solov’eva, E.B.: Fundamentals of Digital Signal Processing. BKhV-Peterburh, SPb (2005). (in Russian)Google Scholar
  12. 12.
    Thonhpanja, S., Phinyomark, A., Phukpattaranont, P., Limsakul, C.: Mean and median frequency of EMG signal to determine muscle force based on time-dependent power spectrum. Elektronika IR Elektrotechnika 19(3), 51–56 (2013)Google Scholar
  13. 13.
    Jahne, B.: Digital Image Processing. Springer, Heidelberg (2005)Google Scholar
  14. 14.
    Fowlkes, C., Martin, D., Malik, J.: Local figure/ground cues are valid for natural images. J. Vis. 7(8)(2), 1–9 (2007)CrossRefGoogle Scholar
  15. 15.
    The Berkeley Segmentation Dataset and Benchmark: BSDS300.
  16. 16.
    Li, J., Rich, W., Buhl-Brown, D.: Texture analysis of remote sensing imagery with clustering and Bayesian inference. Int. J. Image Graph. Sig. Process. (IJIGSP) 7(9), 1–10 (2015).
  17. 17.
    Ye, Z., Yang, J., Zhang, X., Hu, Z.: Remote sensing textual image classification based on ensemble learning. Int. J. Image Graph. Sig. Process. (IJIGSP) 8(12), 21–29 (2016). Scholar
  18. 18.
    Srinivasa Rao, M., Vijaya Kumar, V., Krishna Prasad, M.: Texture classification based on first order local ternary direction patterns. Int. J. Image Graph. Sig. Process. (IJIGSP) 9(2), 46–54 (2017). Scholar
  19. 19.
    Suresha, D., Prakash, H.N.: Data content weighing for subjective versus objective picture quality assessment of natural pictures. Int. J. Image Graph. Sig. Process. (IJIGSP) 9(2), 27–36 (2017). Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Yuriy Fedkovych Chernivtsi National UniversityChernivtsiUkraine

Personalised recommendations