Technology of enhancing image detalization with nonlinear correction of highly gradient fragments
Fursov V.A., Goshin Ye.V., Medvedeva K.S.

 

Samara National Research University, 443086, Samara, Russia, Moskovskoye Shosse 34;

IPSI RAS – Branch of the FSRC “Crystallography and Photonics” RAS, 443001, Samara, Russia, Molodogvardeyskaya 151

 PDF

Abstract:
The article is devoted to the problem of improving the quality of images recorded using low-resolution optical instruments, including diffraction-based cameras. A two-stage image correction technology is proposed. At the first stage, the correction is carried out using a linear FIR filter with a centrally symmetric frequency response in the form of quadratic and exponential functions. The resulting image is then processed with a non-linear filter that performs computer retouching of image areas characterized by a noticeable brightness difference. This procedure is only performed on those pixels in which the absolute value of gradients in different directions is sufficiently high, that is, they are located on the borders of areas with different intensity levels. This allows us to avoid noise amplification in the background, which is typical of traditional filters. The examples of the implementation are provided, showing the possibility of achieving high sharpness and illustrating how the filter can be adjusted by visual perception.

Keywords:
image processing, FIR filter, nonlinear filter, centrally symmetric frequency response, blind identification

Citation:
Fursov VA, Goshin YeV, Medvedeva KS. Technology of enhancing image detalization with nonlinear correction of highly gradient fragments. Computer Optics 2019; 43(3): 484-491. DOI: 10.18287/2412-6179-2019-43-3-484-491.

References:

  1. Pratt W. Digital image processing. New York, NY: John Wiley and Sons Inc; 1978.
  2. Lagendijk R, Biemond J. Basic methods for image restoration and identification. London: Academic Press, 2000.
  3. Soifer VA, ed. Computer image processing, Part II: Methods and algorithms. VDM Verlag Dr. Müller; 2010. ISBN: 978-3-6391-7545-5.
  4. Nikonorov A, Petrov M, Bibikov S, Yuzifovich Y, Yakimov P, Kazanskiy N, Skidanov R, Fursov V. Comparative evaluation of deblurring techniques for Fresnel lens computational imaging. 23rd International Conference on Pattern Recognition (ICPR) 2016: 775-780. DOI: 10.1109/ICPR.2016.7899729.
  5. Nikonorov AV, Petrov MV, Bibikov SA, Kutikova VV, Morozov AA, Kazanskiy NL. Image restoration in diffractive optical systems using deep learning and deconvolution. Computer Optics 2017; 41(6): 875-887. DOI: 10.18287/2412-6179-2017-41-6-875-887.
  6. Steve A. FIR filter design by windowing: Concepts and the rectangular window. Source: <https://www.allabout­circuits.com/technical-articles/finite-impulse-response-filter-design-by-windowing-part-i-concepts-and-rect/>.
  7. Petrou M, Petrou C. Image processing: fundamentals. 2nd ed. Chichester, West Sussex: John Wiley and Sons Ltd; 2010. ISBN: 978-0-470-74586-1.
  8. Nikonorov A, Bibikov S, Myasnikov V, Yuzifovich Y, Fursov V. Correcting color and hyperspectral images with identification of distortion model. Patt Recogn Lett 2016; 83(2): 178-187. DOI: 1016/j.patrec.2016.06.027.
  9. Bavrina AYu, Myasnikov VV, Sergeev AV. Method of parametric estimation of optoelectronics tract of remote sensed optical image formation [In Russian]. Computer Optics 2011; 35(4): 500-507.
  10. Lagendijk R, Biemond J. Basic methods for image restoration and identification. London: Academic Press; 2000.
  11. Saad E, Hirakawa K. Defocus blur-invariant scale-space feature extractions. IEEE Trans Image Proces 2016; 25(7): 3141-3156.
  12. Tian D, Tao D.Coupled learning for facial deblur. IEEE Trans Image Process 2016; 25(2): 961-972.
  13. Peng Y-T, Cosman PC.Underwater image restoration based on image blurriness and light absorption. IEEE Trans Image Process 2017; 26(4): 1579-1594.
  14. Zhu X, Cohen S, Schiller S, Milanfar P. Estimating spatially varying defocus blur from a single image. IEEE Trans Image Process 2013; 22(12): 4879-4891.
  15. Yan R, Shao L. Blind image blur estimation via deep learning. IEEE Trans Image Process 2016; 25(4): 1910-1921.
  16. Huang J, Feng H, Xu Z, Li Q, Chen Y. A robust deblurring algorithm for noisy images with just noticeable blur. Optik 2018; 168: 577-589.
  17. Tan J, Yang K, Song S, Xing T, Fang D. Mobile-deblur: A clear image will on the smart device. 3rd International Conference on Big Data Computing and Communications (BIGCOM) 2017: 97-105.
  18. Mustaniemi J, Kannala J, Särkkä S, Matas J, Heikkilä J. Fast motion deblurring for feature detection and matching using inertial measurements. 24th International Conference on Pattern Recognition (ICPR) 2018: 3068-3073.
  19. Aittala M, Durand F. Burst image deblurring using permutation invariant convolutional neural networks. Proceedings of the European Conference on Computer Vision (ECCV) 2018: 731-747.
  20. Almeida M, Almeida L. Blind and semi-blind deblurring of natural images. IEEE Trans Image Process 2010; 19(1): 36-52.
  21. Fursov VA, Fatkhutdinova EF. The technology of correction of dynamic distortions on mobile devices [In Russian]. CEUR Workshop Proceedings 2018; 2260: 468-479.
  22. Fursov VA. Identification of square-exponential FIR-filter parameters in the absence of a test image. Procedia Engineering 2017; 201: 206-212. DOI: 10.1016/j.proeng.2017.09.611.
  23. Fursov VA. Constructing FIR-filters for a given parametrical class of frequency response for defocus correction [In Russian]. Computer Optics 2016; 40(6): 878-886. DOI: 10.18287/2412-6179-2016-40-6-878-886.
  24. Fursov, VA. Constructing a quadratic-exponential FIR-filter with an extended frequency response midrange [In Russian]. Computer Optics 2018; 42(2): 297-305. DOI: 10.18287/2412-6179-2018-42-2-297-305.
© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846)332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20