Wavelet based retinal recognition

Retina is a new biometric method to recognize a person. The fact that blood vessels have vessels with different thickness and width motivate us to analyze the retina using multi-resolution analysis method. A novel retina feature, named wavelet energy feature (WEF) is defined in this paper, employing wavelet, which is a powerful tool of multi-resolution analysis. WEF can reflect the wavelet energy distribution of the vessels with different thickness and width in several directions at different wavelet decomposition levels (scales), so its ability to discriminate retinas is very strong. Easiness to compute is another virtue of WEF. Using semiconductors and various environmental temperatures in electronic imaging systems cause noisy images, so in this article noisy retinal images are used in recognition. In existence of 5 db to 20 db noise, the proposed method can achieve %100 recognition rates.

[1]  O. Rioul,et al.  Wavelets and signal processing , 1991, IEEE Signal Processing Magazine.

[2]  Sim Heng Ong,et al.  Tooth segmentation of dental study models using range images , 2004, IEEE Transactions on Medical Imaging.

[3]  Stéphane Mallat,et al.  Characterization of Signals from Multiscale Edges , 2011, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Xu Cheng,et al.  The blood vessel recognition of ocular fundus , 2005, 2005 International Conference on Machine Learning and Cybernetics.

[5]  G. Bellala.  Characterization of Signals from Multi scale Edges , 2009 .

[6]  Stéphane Mallat,et al.  Singularity detection and processing with wavelets , 1992, IEEE Trans. Inf. Theory.

[7]  M. Goldbaum,et al.  Detection of blood vessels in retinal images using two-dimensional matched filters. , 1989, IEEE transactions on medical imaging.

[8]  T. Kondo.  Detection of anatomical features in retinal images using a gradient orientation , 2004, 2004 IEEE Region 10 Conference TENCON 2004..