Review and Comparison of Random Spray Retinex and of its variants STRESS and QBRIX

Authors

  • Michela Lecca Fondazione Bruno Kessler, ICT – Technologies of Vision
  • Alessandro Rizzi Università degli Studi di Milano
  • Gabriele Gianini Università degli Studi di Milano

DOI:

https://doi.org/10.23738/ccsj.i92018.06

Keywords:

retinex, spatial color algorithms, color image enhancement

Abstract

In this paper, we review and compare three spatial color algorithms of the Milano Retinex family: Random Spray Retinex (RSR) and its subsequent variants STRESS and QBRIX. These algorithms process the colors of any input image in line with the principles of the Retinex theory, introduced about 50 years ago by Land and McCann to explain how humans see colors. According to this theory, RSR, STRESS and QBRIX re-scale independently the color intensities of each pixel by a quantity, named local reference white, which depends on the spatial arrangement of the colors in the pixel surround. The output is a new color enhanced image that generally has a higher brightness and more visible details than the input one. RSR, STRESS and QBRIX adopt different models of spatial arrangement and implement different equations for the computation of the local reference white, so that they produce different enhanced images. We propose a comparative analysis of their performance based on numerical measures of the image brightness, details and dynamic range. In order to enable result repeatability and further comparisons, we use a set of images publicly available on the net.

Author Biographies

  • Michela Lecca, Fondazione Bruno Kessler, ICT – Technologies of Vision

    Michela Lecca is a permanent researcher of the Fondazione Bruno Kessler (Trento, Italy) by the Research Unit Technologies of Vision, where she works since her graduation in Mathematics. Her research interests include color image processing, low-level image processing for embedded vision systems, object recognition, image retrieval. She is a member of GdC-AIC and of GIRPR-IAPR.

  • Alessandro Rizzi, Università degli Studi di Milano

    Alessandro Rizzi is full professor at the Department of Computer Science of the Università degli Studi di Milano. He is one of the founders of the Italian Color Group, secretary of CIE Division 8, an IS&T Fellow and a past Vice-President. He is topical editor for Applied Color Science of Journal of Optical Society of America A and associate editor of Journal of Electronic Imaging.

  • Gabriele Gianini, Università degli Studi di Milano

    Gabriele Gianini (Ph.D in Physics, 1996), is assistant professor at the Computer Science Department of the Università degli Studi di Milano. He has held visiting positions at INSA de Lyon, University of Passau, EBTIC/Khalifa University at Abu Dhabi, CERN, Fermilab. His research interests include probabilistic modeling, statistical and soft computing techniques and their application image processing.

References

Albers, J. (2009). Interaction of color. New Haven: Yale University Press.

Banić, N., & Lončarić, S. (2013a). Light Random Sprays Retinex: Exploiting the Noisy Illumination Estimation. IEEE Signal Processing Letters, 20(12), pp.1240-1243.

Banić, N., & Lončarić, S. (2013b). Using the Random Sprays Retinex algorithm for global illumination estimation. In 2nd Croatian Computer Vision Workshop.

Creutzfeldt, O., Lange-Malecki, B. and Wortmann, K. (1987). Darkness induction, retinex and cooperative mechanisms

in vision. Experimental Brain Research, 67(2).

De Valois, R. and De Valois, K. (2008). Spatial vision. Oxford: Oxford University Press.

Fierro, M., Ha, H. G., & Ha, Y. H. (2013). Noise reduction based on partial-reference, dual-tree complex wavelet transform shrinkage. IEEE transactions on image processing, 22(5), 1859-1872.

Gianini, G. (2016). Statistical aspects of space sampling in Retinex models. Electronic Imaging, 2016(6), 1-6.

Gianini, G. (2017). From Samples to Populations in Retinex models. Journal of Electronic Imaging (2017) 26.3: 031206-031206.

Gianini, G., Lecca, M., and Rizzi, A. (2016). A population- based approach to point-sampling spatial color algorithms. Journal of the Optical Society of America A, 33(12), 2396-2413.

Gianini, G., Manenti, A. and Rizzi, A. (2014). QBRIX: a quantile-based approach to retinex. Journal of the Optical Society of America A, 31(12), p.2663.

Gianini, G., Rizzi, A. and Damiani, E. (2016). A Retinex model based on Absorbing Markov Chains. Information Sciences, 327, pp.149-174.

Kol s, O., Farup, I. and Rizzi, A. (2011). Spatio-Temporal Retinex-Inspired Envelope with Stochastic Sampling: A Framework for Spatial Color Algorithms. Journal of Imaging Science and Technology, 55(4), p.040503.

Islam, A. T., & Farup, I. (2010). Enhancing the output of spatial color algorithms. In Visual Information Processing (EUVIP), 2010 2nd European Workshop on (pp. 7-12). IEEE.

Islam, A. B. M., & Farup, I. (2011). Spatio-temporal colour correction of strongly degraded movies. Society of Photo Optical Instrumentation Engineers (SPIE).

Land, E. and McCann, J. (1971). Lightness and Retinex Theory. Journal of the Optical Society of America, 61(1), p.1.

Lecca, M., Gianini, G., & Rizzi, A. (2016). Random spray Retinex and its variants STRESS and QBRIX: comparison and experiments on public color images. In XII Conferenza del colore. Multidisciplinary Contributions, vol.XII, n.B, 2016, pp. 41-51. Dipartimento di Architettura e Design, Torino, Italy.

Lecca, M. and Rizzi, A. (2015). Tuning the locality of filtering with a spatially weighted implementation of random spray Retinex. Journal of the Optical Society of America A, 32(10), p.1876.

Lecca M., Rizzi A., Gianini G.

Lecca, M., Rizzi, A. and Gianini, G. (2015). Energy-driven path search for Termite Retinex. Journal of the Optical Society of America A, 33(1), p.31.

Marini, D. and Rizzi, A. (2000). A computational approach to color adaptation effects. Image and Vision Computing, 18(13), pp.1005-1014.

McCann, J. and Rizzi, A. (2012). The art and science of HDR imaging. Chichester, West Sussex, U.K.: Wiley.

Montagna, R. and Finlayson, G. (2011). Constrained pseudo-Brownian motion and its application to image enhancement. Journal of the Optical Society of America A, 28(8), p.1677.

Provenzi, E., Fierro, M., Rizzi, A., De Carli, L., Gadia, D. and Marini, D. (2007). Random Spray Retinex: A New Retinex Implementation to Investigate the Local Properties of the Model. IEEE Transactions on Image Processing, 16(1), pp.162-171.

Provenzi, E., Marini, D., De Carli, L. and Rizzi, A. (2005). Mathematical definition and analysis of the Retinex algorithm. Journal of the Optical Society of America A, 22(12), p.2613.

Rizzi, A., Algeri, T., Medeghini, G., & Marini, D. (2004). A proposal for contrast measure in digital images. In Conference on colour in graphics, imaging, and vision (Vol. 2004, No. 1, pp. 187-192). Society for Imaging Science and Technology.

Rizzi, A. and Bonanomi, C. (2017). Milano Retinex family. Journal of Electronic Imaging, 26(3), p.031207.

Rizzi, A. and Parraman, C. (2010). Developments in the recovery of colour in fine art prints using spatial image processing. Journal of Physics: Conference Series, 231, p.012003.

Rizzi, A., Gatta, C. and Marini, D. (2003a). A new algorithm for unsupervised global and local color correction. Pattern Recognition Letters, 24(11), pp.1663-1677.

Rizzi, A., Gatta, C., & Marini, D. (2003b). YACCD: Yet Another Color Constancy Database. In Color Imaging: Processing, Hardcopy, and Applications (pp. 24-35).

Rizzi, A. and McCann, J. J. (2007). On the behavior of spatial models of color. In Color Imaging: Processing, Hardcopy, and Applications (p. 649302).

Simone, G., Audino, G., Farup, I., Albregtsen, F. and Rizzi, A. (2014). Termite Retinex: a new implementation based on a colony of intelligent agents. Journal of Electronic Imaging, 23(1), p.013006.

Simone, G., Cordone, R., Serapioni, R. and Lecca, M. (2017). On edge-aware path-based color spatial sampling for Retinex: from Termite Retinex to Light Energy-driven Termite Retinex. Journal of Electronic Imaging, 26(3), p.031203

Downloads

Published

2018-04-19

Issue

Section

Papers

How to Cite

“Review and Comparison of Random Spray Retinex and of its variants STRESS and QBRIX” (2018) Cultura e Scienza del Colore - Color Culture and Science, 9, pp. 55–64. doi:10.23738/ccsj.i92018.06.