Retrospective Illumination Correction of Retinal Images

A method for correction of nonhomogenous illumination based on optimization of parameters of B-spline shading model with respect to Shannon's entropy is presented. The evaluation of Shannon's entropy is based on Parzen windowing method (Mangin, 2000) with the spline-based shading model. This allows us to express the derivatives of the entropy criterion analytically, which enables efficient use of gradient-based optimization algorithms. Seven different gradient- and nongradient-based optimization algorithms were initially tested on a set of 40 simulated retinal images, generated by a model of the respective image acquisition system. Among the tested optimizers, the gradient-based optimizer with varying step has shown to have the fastest convergence while providing the best precision. The final algorithm proved to be able of suppressing approximately 70% of the artificially introduced non-homogenous illumination. To assess the practical utility of the method, it was qualitatively tested on a set of 336 real retinal images; it proved the ability of eliminating the illumination inhomogeneity substantially in most of cases. The application field of this method is especially in preprocessing of retinal images, as preparation for reliable segmentation or registration.

[1]  J. Mangin,et al.  Entropy minimization for automatic correction of intensity nonuniformity , 2000, Proceedings IEEE Workshop on Mathematical Methods in Biomedical Image Analysis. MMBIA-2000 (Cat. No.PR00737).

[2]  H. Niemann,et al.  Towards automated diagnostic evaluation of retina images , 2006, Pattern Recognition and Image Analysis.

[3]  Nanning Zheng,et al.  Shading extraction and correction for scanned book images , 2008, IEEE Signal Processing Letters.

[4]  J. Haselgrove,et al.  An algorithm for compensation of surface-coil images for sensitivity of the surface coil , 1986 .

[5]  Stuart C. Schwartz,et al.  General illumination correction and its application to face normalization , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[6]  David H. Miller,et al.  Correction for variations in MRI scanner sensitivity in brain studies with histogram matching , 1998, Magnetic resonance in medicine.

[7]  M. Montaz Ali,et al.  A Numerical Comparison of Some Modified Controlled Random Search Algorithms , 1997, J. Glob. Optim..

[8]  Enrico Grisan,et al.  Luminosity and contrast normalization in retinal images , 2005, Medical Image Anal..

[9]  Michael Unser,et al.  B-spline signal processing. I. Theory , 1993, IEEE Trans. Signal Process..

[10]  R. Lufkin,et al.  Dynamic-range compression in surface-coil MRI. , 1986, AJR. American journal of roentgenology.

[11]  Danilo P. Mandic,et al.  A generalized normalized gradient descent algorithm , 2004, IEEE Signal Processing Letters.

[12]  Aly A. Farag,et al.  Bias field estimation and adaptive segmentation of MRI data using a modified fuzzy C-means algorithm , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[13]  Peter F. Sharp,et al.  Automated microaneurysm detection using local contrast normalization and local vessel detection , 2006, IEEE Transactions on Medical Imaging.

[14]  W. B. Seales,et al.  Restoring 2D Content from Distorted Documents , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  I T Young,et al.  Shading Correction: Compensation for Illumination and Sensor Inhomogeneities , 2000, Current protocols in cytometry.

[16]  Richard A. Robb,et al.  Optimized homomorphic unsharp masking for MR grayscale inhomogeneity correction , 1998, IEEE Transactions on Medical Imaging.

[17]  Bostjan Likar,et al.  Segmentation-based retrospective correction of intensity nonuniformity in multispectral MR images , 2002, SPIE Medical Imaging.

[18]  J. Jan,et al.  Registration of bimodal retinal images - improving modifications , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[19]  Benoit M. Dawant,et al.  Correction of intensity variations in MR images for computer-aided tissue classification , 1993, IEEE Trans. Medical Imaging.

[20]  L. Axel,et al.  Intensity correction in surface-coil MR imaging. , 1987, AJR. American journal of roentgenology.

[21]  W. Eric L. Grimson,et al.  Adaptive Segmentation of MRI Data , 1995, CVRMed.

[22]  Viergever,et al.  Retrospective shading correction based on entropy minimization , 2000, Journal of microscopy.

[23]  Akram Aldroubi,et al.  B-SPLINE SIGNAL PROCESSING: PART I-THEORY , 1993 .

[24]  Martin Styner,et al.  Parametric estimate of intensity inhomogeneities applied to MRI , 2000, IEEE Transactions on Medical Imaging.

[25]  Michael Brady,et al.  Estimating the bias field of MR images , 1997, IEEE Transactions on Medical Imaging.

[26]  Alan C. Evans,et al.  A nonparametric method for automatic correction of intensity nonuniformity in MRI data , 1998, IEEE Transactions on Medical Imaging.

[27]  Dorin Comaniciu,et al.  Total variation models for variable lighting face recognition , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Aliaa A. A. Youssif,et al.  Optic Disc Detection From Normalized Digital Fundus Images by Means of a Vessels' Direction Matched Filter , 2008, IEEE Transactions on Medical Imaging.

[29]  Jorge Nocedal,et al.  On the limited memory BFGS method for large scale optimization , 1989, Math. Program..

[30]  Jirí Jan,et al.  Registration and Fusion of the Autofluorescent and Infrared Retinal Images , 2008, Int. J. Biomed. Imaging.

[31]  William H. Press,et al.  Numerical recipes in C , 2002 .