Retinal biometrics has been very handy in most parts of the world with respect to diabetic retinopathy. In diabetic retinopathy, the most complicated part comes when patients loose their eye sight. This is called as Macular Degeneration. Macular Degeneration comes in two stages. The first stage is when clinically significant features are present on the retina, the second stage is when non clinically significant features are present on the retina. Clinically significant features are present near the macula which is the center of retina. Non clinical features which are also called artifacts which are distortions on the retina are present on the periphery. In this paper the main focus has been on the clinically significant features. The clinically significant features are micro-aneurysms, hemorrhages and exudates. In this paper the main concentration has been on the degeneration of macula. The macula is the region of illumination on the retina. The extraction of micro-aneurysms has been based on the red component of the retinal image. Similarly the extraction of hemorrhages and exudates has been based on the other color components. The extraction of macula has been based on the texture of retinal images. The goal of this paper is to device a method which constricts the region of the macula depending on high or low intensity regions. Based on this goal , the two main objectives which were defined are fixing the regions of macula and then deciding on which stage of diabetes , the person is in. Lots of research has been done in the area of extracting the basic diabetic features which are based on filters like the gabor filter. The scope in the area of extracting the macula has been very limited because the intensities of the vessels and macula is same in the gray scale image. Therefore in this paper an attempt has been made to extract the macula using textures. The most serious stage of diabetes is blindness where macular degeneration is seen. Keeping in mind the real life threats from macular degeneration, efforts have been made in this paper to correlate biometrics and macular degeneration with respect to retinal images. With respect to classification of retinal images, macular degeneration gives lot of insight into the reasons for blindness of a person.

1. Helga , K. (2003). How the retina works, The Scientific Research Society.
2. Xueming, W. , Hongbao, C. , Jie, Z. (2005). Analysis of retinal images associated with hypertension and diabetes, IEEE transactions on Medical Imaging, Vol 11, No 3, pp34-43.
3. Tien, W. , Paul, M. (2010). The eye of hypertension, www. thelancet. com, pp 35-46.
4. Connor, H. , John, F. , Michael, O. , Mark, C. (2002). Characterization of changes in the blood vessels width and tortuosity in retinopathy of prematurity using image analysis, Journal of Medical Image Analysis , Vol 31, No4, pp 407-429.
5. Koichiro, A. , Hidlki, K. (1982). A computer method of understanding Ocular fundus images, Pattern recognition, Vol. 15, No 6, pp 431-443 .
6. Balaji, G. , Dhananjay, T. , Rupert, Y. ,Chris, C. (2006). Biometric iris recognition system using a fast and robust iris localization and alignment procedure, Journal of Optics and Lasers in Engineering, Vol 3, No 2, pp 1-24.
7. Forest, D. E. , MD. (2010). Selected pigmented fundus lesions of children, Journal of Aapos, Vol 3,No 1, pp 4-10.
8. Robert, A. E. , MD, Thuy, H. N. , MD, Donald, J. G. , MD, Joseph, F. R. , MD, John, T. , and John, O. S. , MD. (2009). Retinal arterial wall plagues in susac syndrome, IEEE transactions on Medical Imaging, Vol 4, No 5, pp 6-11.
9. Niall, P. , Mrcophth, K. , Rishma, M. , Bsc, Tom, M. , PhD, and Baljean, D. F. (2005). Effect of axial length on retinal vascular network geometry, IEEE transactions on Medical Imaging, Elsevier, Vol 6, No 7, pp 4-9.
10. Christian, N. M. and Chu, H. K. , et-al. (2007). Application of data envelop analysis in bench marking, International Journal of Quality Science, Vol. 3 , No. 4, pp 320-327.
11. Acharya, U. R. , Min, L. C. , Ng, E. Y. K. , Chee, C. , Tamura, T. (2009). Computer based detection of diabetes retinopathy stages using digital fundus images, Journal of Engineering in Medicine, Vol. 223, No5, pp 15-27.
12. . Adam, H. , Valentina, K. , Michael, G. (1998). Locating Blood vessels in Retinal images by Piece-wise Threshold probing of a Matched filter response, International Journal of Biomedicine, Vol 21, No 7, pp 931-935.
13. Rashindra, M. , Wiro, N. (1998). Local Speed Functions in Level set based Level Segmentation, International Journal of Biomedicine, Vol 23, No 4, pp 475-482.
14. David, C. K. , Daniel, M. S. (2005). An Economic Analysis of interventions of Diabetes, Diabetes Care, International Journal of Biomedicine, Vol. 23, No 3, pp 3-6.
15. Chutatape, O. , Liu, Z. , Krishna, S. M. (1998). Retinal Blood Vessel Detection and Tracking, Proceedings of the 20th Annual International Conference of IEEE Engg in Medicine and Biology Society, Vol. 20, No 6, pp 11-19.
16. Zana, F. , Klein, J. C. (2009). A Multimodal Registration Algorithm of Eye Fundus images using Vessels Detection and Hough Transform, IEEE Transactions on Medical Imaging, Vol. 18, No 5, pp 23-31.
17. Yannis, A. T. , Stavros, M. P. (1997). An Unsupervised Fuzzy Vessel Tracking Algorithm for Retinal Images, IEEE Transactions on Medical Imaging, Vol 20, No 5, pp 325-329.
18. Ali, C. , Hong, S. , James, N. T. , et-al(1999). Rapid Automated Tracing and Feature Extraction from Retinal Fundus Images using Direct Exploratory Algorithms, IEEE Transactions on Information Technology in Bio-Medicine, Vol. 3, No 2, pp 65-78.

(x y) As Image Theta For Angle X And Y For Coordinates Sqrt For Square Root Arctan For Calculating Inclination