Fast normalized cross-correlation based retinal recognition

In this paper, a simple biometric scheme based on RGB retinal fundus images is proposed. First, prominent vasculature energy based feature vectors are constructed from RGB retinal fundus images to utilize the unique pattern of retinal vasculature. Next, fast normalized cross-correlation based feature matching is employed for person identification on publicly available DRIVE and STARE databases. This method excels recently published literatures with perfect recognition accuracy of 100% on STARE and accuracy of 99.77% on DRIVE databases. Its smaller dimension of feature vector and better recognition result make this method eligible for real-time person identification scheme.

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

[2]  A.M. Fard,et al.  A o el uman Identifier System usin Retina Ima e and u y Clusterin , 2006, 2006 2nd International Conference on Information & Communication Technologies.

[3]  Ratnadeep R. Deshmukh,et al.  Analysis of Retina Recognition by Correlation and Covariance Matrix , 2010, 2010 3rd International Conference on Emerging Trends in Engineering and Technology.

[4]  Ryszard S. Choras,et al.  Retina recognition for biometrics , 2012, Seventh International Conference on Digital Information Management (ICDIM 2012).

[5]  Mansour Vafadoost,et al.  Wavelet based retinal recognition , 2007, 2007 9th International Symposium on Signal Processing and Its Applications.

[6]  Pascale Massin,et al.  Automatic detection of microaneurysms in color fundus images , 2007, Medical Image Anal..

[7]  Hamid Abrishami Moghaddam,et al.  A Novel Retinal Identification System , 2008, EURASIP J. Adv. Signal Process..

[8]  S. Reza Hadianamrei,et al.  Retinal Identification System Based on the Combination of Fourier and Wavelet Transform , 2012 .

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

[10]  José Manuel Bravo,et al.  A New Supervised Method for Blood Vessel Segmentation in Retinal Images by Using Gray-Level and Moment Invariants-Based Features , 2011, IEEE Transactions on Medical Imaging.

[11]  Shubhra Aich,et al.  An Efficient Supervised Approach for Retinal Person Identification using Zernike Moments , 2013 .

[12]  M. Usman Akram,et al.  Retinal recognition: Personal identification using blood vessels , 2011, 2011 International Conference for Internet Technology and Secured Transactions.

[13]  S. Qamber,et al.  Personal identification system based on vascular pattern of human retina , 2012, 2012 Cairo International Biomedical Engineering Conference (CIBEC).

[14]  J. P. Lewis.  Fast Normalized Cross-Correlation , 2010 .

[15]  L. Latha,et al.  Efficient Approach for Retinal Biometric Template Security and Person Authentication using Noninvertible Constructions , 2013 .

[16]  Wafa Barkhoda,et al.  Retina identification based on the pattern of blood vessels using fuzzy logic , 2011, EURASIP J. Adv. Signal Process..

[17]  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.