Diabetic Retinopathy is one of the leading causes of blindness. Hard exudates have been found to be one of the most prevalent earliest clinical signs of retinopathy. Thus, identification and classification of hard exudates from retinal images is clinically significant. For this purpose the images from the hospitals were taken as reference. In this work, Genetic Algorithm (GA) for best feature selection from retinal images is proposed. The features that improve the classification accuracy are selected by Genetic Algorithm and termed as optimized feature set. The others that degrade the performance are rejected at the end of specified generation (in this case 100 generations).

1. Clara I. Sánchez , María García , Agustín Mayo , María I.López , Roberto Hornero , May 2009, “Retinal image analysis based on mixture models to detect hard exudates”, Journal for Medical Image Analysis, Journal for Medical Image Analysis, Vol. 13 ,pp.650-658.
2. Wong li yun, U. Rajendra Acharya, Y.V. Venkatesh, Caroline Chee, Lim Choo Min, E.Y.K. Ng. 2008,“ Identification of different stages of diabetic retino- pathy using retinal optical images”, Information Sciences, Vol. 178, pp.106–121.
3. R. Acharya U, L.Y. Wong, E.Y.K. Ng, J.S. Suri, 2007, “Automatic identification of anterior segment eye abnormality”, Journal of ITBM-RBM, Vol. 28, pp. 35–41.
4. Il-Seok Oh, Member IEEE, Jin-Seon Lee, and Byung-Ro Moon, Member IEEE, Nov 2004, “Hybrid genetic algorithms for feature selection”, IEEE Transactions On Pattern Analysis And Machine Intelligence, Vol. 26, No.11, pp.1424-1437 Retinal Image Features Optimized Retinal Image Features Mean, Standard Deviation, Variance, Entropy, Contrast, Correlation, Energy, Homogeneity, Angular Second Moment, Inverse Differential Moment, Skewness, Area, Mean Intensity, Minimum Intensity, Euler Mean, Variance, Entropy, Energy, Homogeneity, Angular Second moment, Inverse Differential moment, Area, Mean Intensity, Minimum Intensity
5. Enrique J. Carmona , Mariano Rincon , Julian Garcia- Feijoo Jose M. Martinez-De-La-Casa, 2008, “Identification of the optic nerve head with genetic algorithms”, Artificial Intelligence In Medicine,Vol.43, pp. 243—259.
6. Hiroshi Someya, Member, IEEE, April 2011,“ Theoretical analysis of phenotypic diversity in real-valued evolutionary algorithms with more-than-one element replacement”, IEEE Transactions On Evolutionary Computation, Vol.15, No.2, pp.248-266.
7. Michael L. Raymer, William F. Punch, Erik D. Goodman, Leslie A. Kuhn, And Anil K. Jain, July 2000, “Dimensionality reduction using genetic algorithms”, IEEE Transactions On Evolutionary Computation”, Vol. 4, No. 2, pp.164-172.
8. P.M.Narendra, and K. Fukunaga, 1977 “A branch and bound algorithm for feature selection,” IEEE Transactions on Computers, 26(9), 917-922 .
9. I. Foroutan, and J. Sklansky, 1987. “Feature selection for automatic classification of non-Gaussian data,” IEEE Transactions on System, Man and Cybernetics, 17,187-198
10. D.E.Goldberg.,1989.”Genetic Algorithms in Search, Optimization and Machine Learning, Addison-Wesley Reading ,MA
11. J.H. Holland.,1975.., Adaptation in Natural and Artificial System, University of Michigan Press, Ann Arbor, MI
12. W.Siedlecki and J. Sklansky, 1989. “A note on Genetic algorithms for large-scale feature selection,” Pattern Recognition Letters, 10, 335-347
13. M. Kudo and J. Sklansky, 2000. “Comparison of Algorithms that select features for pattern classifiers,” Pattern Recognition, 33, 25-41.
14. M.R.Peterson, T.E.Doom, and M.L.Raymer, 2004. “GA facilitated knowledge discovery and pattern recognition optimization applied to the biochemistry of protein salvation. In GECCO 2004 proceedings, LNCS,3102, 426-437.

Diabetic retinopathy hard exudates retinal images Genetic Algorithm (GA)