Noise-robust low-contrast retinal recognition using compression-based joint wavelet transform correlator

Abstract A new method is proposed for recognizing noise corrupted low-contrast retinal images that employs joint wavelet transform correlator with compressed reference and target. Noise robustness is achieved by correlating wavelet-transformed retinal target and reference images. Simulation results show that besides being robust to noise, its recognition performance can become independent upon compression qualities when low spatial-frequency components of joint power spectrum are enhanced by appropriately dilated wavelet filter.

[1]  D A Gregory,et al.  Effects of thresholding in joint-transform correlation. , 1992, Applied optics.

[2]  Justis P. Ehlers,et al.  The Wills Eye Manual: Office and Emergency Room Diagnosis and Treatment of Eye Disease , 2010 .

[3]  Joewono Widjaja,et al.  Experimental verifications of noise suppression in retinal recognition by using compression-based joint transform correlator , 2014 .

[4]  A. Basu,et al.  Is digital image compression acceptable within diabetic retinopathy screening? , 2003, Diabetic medicine : a journal of the British Diabetic Association.

[5]  Mohammad S. Alam,et al.  Optoelectronic implementation of fringe-adjusted joint transform correlation , 2004 .

[6]  Joewono Widjaja,et al.  Real-time joint transform correlator using compressed reference images , 2004 .

[7]  A Erginay,et al.  Evaluation of the effect of JPEG and JPEG2000 image compression on the detection of diabetic retinopathy , 2007, Eye.

[8]  Arun Ross,et al.  An introduction to biometric recognition , 2004, IEEE Transactions on Circuits and Systems for Video Technology.

[9]  Hongchen Zhai,et al.  Use of laser diode in joint transform correlator , 2004 .

[10]  I. Deary,et al.  Retinal image analysis: Concepts, applications and potential , 2006, Progress in Retinal and Eye Research.

[11]  Y Sheng,et al.  Optical wavelet matched filter. , 1994, Applied optics.

[12]  M. N. Islam,et al.  Distortion-invariant pattern recognition using synthetic discriminant function based multiple phase-shifted-reference fringe-adjusted joint transform correlation , 2011 .

[13]  Montserrat Corbalán Fuertes,et al.  Joint transform correlator , 2006 .

[14]  A.D. Hoover,et al.  Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response , 2000, IEEE Transactions on Medical Imaging.

[15]  Stephen A. Davis,et al.  Retina Verification System Based on Biometric Graph Matching , 2013, IEEE Transactions on Image Processing.

[16]  Joewono Widjaja.  Detection performance of wavelet-based joint transform correlation. , 2007, Applied optics.

[17]  J. Goodman.  Introduction to Fourier optics , 1969 .

[18]  Ingrid Daubechies,et al.  Ten Lectures on Wavelets , 1992 .

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

[20]  Joewono Widjaja,et al.  Retina recognition using compression-based joint transform correlator , 2011 .

[21]  P. Tower.  The fundus oculi in monozygotic twins; report of six pairs of identical twins. , 1955, A.M.A. archives of ophthalmology.

[22]  Joan L. Mitchell,et al.  JPEG: Still Image Data Compression Standard , 1992 .

[23]  Mohammad S. Alam,et al.  Adaptive nonlinear fringe-adjusted joint transform correlator , 2012 .

[24]  David Zhang,et al.  A Modified Matched Filter With Double-Sided Thresholding for Screening Proliferative Diabetic Retinopathy , 2009, IEEE Transactions on Information Technology in Biomedicine.

[25]  D. Singer,et al.  Screening for Diabetic Retinopathy , 1993, Diabetes Care.

[26]  Ana Maria Mendonça,et al.  Segmentation of retinal blood vessels by combining the detection of centerlines and morphological reconstruction , 2006, IEEE Transactions on Medical Imaging.