Issues About Retinex Theory and Contrast Enhancement

AbstractWe present an interpretation of Land’s Retinex theory that we show to be consistent with the original formulation. The proposed model relies on the computation of the expectation value of a suitable random variable weighted with a kernel function, thus the name Kernel-Based Retinex (KBR) for the corresponding algorithm. KBR shares the same intrinsic characteristics of the original Retinex: it can reduce the effect of a color cast and enhance details in low-key images but, since it can only increase pixel intensities, it is not able to enhance over-exposed pictures. Comparing the analytical structure of KBR with that of a recent variational model of color image enhancement, we are able to perform an analysis of the action of KBR on contrast, showing the need to anti-symmetrize its equation in order to produce a two-sided contrast modification, able to enhance both under and over-exposed pictures. The anti-symmetrized KBR equations show clear correspondences with other existing color correction models, in particular ACE, whose relationship with Retinex has always been difficult to clarify. Finally, from an image processing point of view, we mention that both KBR and its antisymmetric version are free from the chromatic noise due to the use of paths in the original Retinex implementation and that they can be suitably approximated in order to reduce their computational complexity from $\mathcal{O}(N^{2})$ to $\mathcal{O}(N\log N)$ , being N the number of input pixels.

[1]  John J. McCann,et al.  Retinex in Matlab , 2000, CIC.

[2]  Zia-ur Rahman,et al.  A multiscale retinex for bridging the gap between color images and the human observation of scenes , 1997, IEEE Trans. Image Process..

[3]  Carlo Gatta,et al.  A new algorithm for unsupervised global and local color correction , 2003, Pattern Recognit. Lett..

[4]  Alessandro Rizzi,et al.  Mathematical definition and analysis of the retinex algorithm. , 2005, Journal of the Optical Society of America. A, Optics, image science, and vision.

[5]  S. McKee,et al.  Quantitative studies in retinex theory a comparison between theoretical predictions and observer responses to the “color mondrian” experiments , 1976, Vision Research.

[6]  Alessandro Rizzi,et al.  Perceptual Color Correction Through Variational Techniques , 2007, IEEE Transactions on Image Processing.

[7]  Marcelo Bertalmío,et al.  Implementing the Retinex algorithm with Wilson–Cowan equations , 2009, Journal of Physiology-Paris.

[8]  E H Land,et al.  An alternative technique for the computation of the designator in the retinex theory of color vision. , 1986, Proceedings of the National Academy of Sciences of the United States of America.

[9]  Andrew Blake,et al.  Boundary conditions for lightness computation in Mondrian World , 1985, Comput. Vis. Graph. Image Process..

[10]  E. Land,et al.  Lightness and retinex theory. , 1971, Journal of the Optical Society of America.

[11]  Alessandro Rizzi,et al.  A computational approach to color adaptation effects , 2000, Image Vis. Comput..

[12]  Zia-ur Rahman,et al.  Properties and performance of a center/surround retinex , 1997, IEEE Trans. Image Process..

[13]  John J. McCann,et al.  Capturing a black cat in shade: past and present of Retinex color appearance models , 2004, J. Electronic Imaging.

[14]  J. Cowan,et al.  A mathematical theory of the functional dynamics of cortical and thalamic nervous tissue , 1973, Kybernetik.

[15]  Carlo Gatta,et al.  From Retinex to Automatic Color Equalization: issues in developing a new algorithm for unsupervised color equalization , 2004, J. Electronic Imaging.

[16]  Berthold K. P. Horn,et al.  Determining lightness from an image , 1974, Comput. Graph. Image Process..

[17]  Martin Golubitsky,et al.  What Geometric Visual Hallucinations Tell Us about the Visual Cortex , 2002, Neural Computation.

[18]  Edoardo Provenzi,et al.  A Perceptually Inspired Variational Framework for Color Enhancement , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  E H Land,et al.  Recent advances in retinex theory and some implications for cortical computations: color vision and the natural image. , 1983, Proceedings of the National Academy of Sciences of the United States of America.

[20]  J. Cowan,et al.  Excitatory and inhibitory interactions in localized populations of model neurons. , 1972, Biophysical journal.

[21]  L. G. Glasser,et al.  Cube-Root Color Coordinate System , 1958 .

[22]  E. Land.  The retinex theory of color vision. , 1977, Scientific American.

[23]  Roberto Manduchi,et al.  Bilateral filtering for gray and color images , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[24]  D Marr,et al.  The computation of lightness by the primate retina. , 1974, Vision research.

[25]  Carlo Gatta,et al.  A Spatially Variant White-Patch and Gray-World Method for Color Image Enhancement Driven by Local Contrast , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  A Hurlbert,et al.  Formal connections between lightness algorithms. , 1986, Journal of the Optical Society of America. A, Optics and image science.

[27]  John J. McCann,et al.  Retinex in MATLABTM , 2004, J. Electronic Imaging.

[28]  Danny Barash,et al.  A Fundamental Relationship between Bilateral Filtering, Adaptive Smoothing, and the Nonlinear Diffusion Equation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[29]  Alessandro Rizzi,et al.  Random Spray Retinex: A New Retinex Implementation to Investigate the Local Properties of the Model , 2007, IEEE Transactions on Image Processing.

[30]  Michael Elad,et al.  A Variational Framework for Retinex , 2002, IS&T/SPIE Electronic Imaging.

[31]  Farhan A. Baqai,et al.  Analysis and extensions of the Frankle-McCann Retinex algorithm , 2004, J. Electronic Imaging.

[32]  L. Ambrosio,et al.  Gradient Flows: In Metric Spaces and in the Space of Probability Measures , 2005 .