Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
Springer Nature Link
Log in

Learning to Deblur Adaptive Optics Retinal Images

  • Conference paper
  • First Online:
Image Analysis and Recognition (ICIAR 2017)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 10317))

Included in the following conference series:

Abstract

In this paper we propose a blind deconvolution approach for reconstruction of Adaptive Optics (AO) high-resolution retinal images. The framework employs Random Forest to learn the mapping of retinal images onto the space of blur kernels expressed in terms of Zernike coefficients. A specially designed feature extraction technique allows inference of blur kernels for retinal images of various quality, taken at different locations of the retina. This model is validated on synthetically generated images as well as real AO high-resolution retinal images. The obtained results on the synthetic data showed an average root-mean-square error of 0.0051 for the predicted blur kernels and 0.0464 for the reconstructed images, compared to the ground truth (GT). The assessment of the reconstructed AO retinal images demonstrated that the contrast, sharpness and visual quality of the images have been significantly improved.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Similar content being viewed by others

References

  1. Rao, C., Yu, T., Hua, B.: Topics in adaptive optics. AO-based high resolution image post-processing. In: Tyson, R.K. (eds.) Topics in Adaptive Optics, pp. 69–94. InTech (2012)

    Google Scholar 

  2. Arines, J.: Partially compensated deconvolution from wavefront sensing images of the eye fundus. Opt. Commun. 284(6), 1548–1552 (2011)

    Article  Google Scholar 

  3. Christou, J.C., Roorda, A., Williams, D.R.: Deconvolution of adaptive optics retinal images. J. Opt. Soc. Am. A. Opt. Image Sci. Vis. 21(8), 1393–1401 (2004)

    Article  Google Scholar 

  4. Blanco, L., Mugnier, L.M.: Marginal blind deconvolution of adaptive optics retinal images. Opt. Express 19(23), 23227 (2011)

    Article  Google Scholar 

  5. Li, H., Lu, J., Shi, G., Zhang, Y.: Real-time blind deconvolution of retinal images in adaptive optics scanning laser ophthalmoscopy. Opt. Commun. 284(13), 3258–3263 (2011)

    Article  Google Scholar 

  6. Chenegros, G., Mugnier, L.M., Lacombe, F., Glanc, M.: 3D phase diversity: a myopic deconvolution method for short-exposure images: application to retinal imaging. J. Opt. Soc. Am. A 24(5), 1349 (2007)

    Article  Google Scholar 

  7. Fanello, S.R., Keskin, C., Kohli, P., Izadi, S., Shotton, J., Criminisi, A., Pattacini, U., Paek T.: Filter forests for learning data-dependent convolutional kernels. In: IEEE CVPR, pp. 1709–1716 (2014)

    Google Scholar 

  8. Schuler, C.J., Burger, H.C., Harmeling, S., Scholkopf, B.: A machine learning approach for non-blind image deconvolution. In: IEEE CVPR, pp. 1067–1074 (2013)

    Google Scholar 

  9. Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. CVPR 1, 886–893 (2005)

    Google Scholar 

  10. Lazareva, A., Liatsis, P., Rauscher, F.G.: An automated image processing system for the detection of photoreceptor cells in adaptive optics retinal images. In: IWSSIP, pp. 196–199 (2015)

    Google Scholar 

  11. Atchison, D.A., Bradley, A., Thibos, L.N., Smith, G.: Useful variations of the Badal Optometer. Optom. Vis. Sci. 72(4), 279–284 (1995)

    Article  Google Scholar 

  12. Noll, R.J.: Zernike polynomials and atmospheric turbulence. J. Opt. Soc. Am. 66(3), 207 (1976)

    Article  MathSciNet  Google Scholar 

  13. Thibos, L.N., Bradley, A., Hong, X.: A statistical model of the aberration structure of normal, well-corrected eyes. Ophthalmic Physiol. Opt. 22(5), 427–433 (2002)

    Article  Google Scholar 

  14. Valeshabad, A.K., Wanek, J., Grant, P., Lim, J.I., Chau, F.Y., Zelkha, R., Camardo, N., Shahidi, M.: Wavefront error correction with adaptive optics in diabetic retinopathy. Optom. Vis. Sci. 91(10), 1238–1243 (2014)

    Article  Google Scholar 

  15. Mariotti, L., Devaney, N.: Performance analysis of cone detection algorithms. J. Opt. Soc. Am. A 32(4), 497 (2015)

    Article  Google Scholar 

  16. Lazareva, A., Liatsis, P., Rauscher, F.G.: Hessian-LoG filtering for enhancement and detection of photoreceptor cells in adaptive optics retinal images. J. Opt. Soc. Am. A 33(1), 84 (2015)

    Article  Google Scholar 

  17. Lucy, L.B.: An iterative technique for the rectification of observed distributions. Astron. J. 79, 745 (1974)

    Article  Google Scholar 

  18. Richardson, W.H.: Bayesian-based iterative method of image restoration. J. Opt. Soc. Am. 62(1), 55 (1972)

    Article  Google Scholar 

  19. Sroubek, F., Milanfar, P.: Robust multichannel blind deconvolution via fast alternating minimization. IEEE Trans. Image Process. 21(4), 1687–1700 (2012)

    Article  MathSciNet  Google Scholar 

  20. Peli, E.: Contrast in complex images. J. Opt. Soc. Am. A 7(10), 2032 (1990)

    Article  Google Scholar 

  21. Kanjar, D., Masilamani, V.: A new no-reference image quality measure for blurred images in spatial domain. J. Image Graph. 1(1), 39–42 (2013)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Electrical and Electronic Engineering, City, University of London, London, UK

    Anfisa Lazareva

  2. Department of Computer Science, City, University of London, London, UK

    Muhammad Asad & Greg Slabaugh

Authors
  1. Anfisa Lazareva
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Muhammad Asad
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Greg Slabaugh
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Anfisa Lazareva .

Editor information

Editors and Affiliations

  1. University of Waterloo, Waterloo, ON, Canada

    Fakhri Karray

  2. University of Porto, Porto, Portugal

    Aurélio Campilho

  3. Politechnique Montreal, Montreal, QC, Canada

    Farida Cheriet

Rights and permissions

Reprints and permissions

Copyright information

© 2017 Springer International Publishing AG

About this paper

Cite this paper

Lazareva, A., Asad, M., Slabaugh, G. (2017). Learning to Deblur Adaptive Optics Retinal Images. In: Karray, F., Campilho, A., Cheriet, F. (eds) Image Analysis and Recognition. ICIAR 2017. Lecture Notes in Computer Science(), vol 10317. Springer, Cham. https://doi.org/10.1007/978-3-319-59876-5_55

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-59876-5_55

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-59875-8

  • Online ISBN: 978-3-319-59876-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation