At present, Diabetic Retinopathy was considered as the main cause of blindness for diabetic patients. The Diabetic Retinopathy can be identified at an earlier stage by detecting the microaneurysms in the retina of the patients. For this purpose, opthalmologists will regularly supervise the retinal images obtained using the color fundus camera. During this regular supervision the ophthalmologists should spend more amount of time and energy. The space required to store the normal and abnormal retinal images will also increases. A new method for detecting the microaneurysms from the color fundus retinal image based on feature classification was proposed in this project, to reduce the ophthalmologists' time and energy for verifying the retinal images. The microaneurysms are detected from the color fundus image by applying the preprocessing techniques inorder to remove the optic disk and similar blood vessels using morphological operations. The preprocessed image was then used for feature extraction and these features were used for classification purpose. The classifier used is Support Vector Machine which improves sensitivity, specificity and gives an average accuracy of 90%.

1. Akara Sopharak, Bunyarit Uyyanonvara, Sarah barman (2011) 'Automatic Microaneurysm Detection from Non-dilated Diabetic Retinopathy Retinal Images Using Mathematical Morphology Methods', IAENG International Journal of Computer Science, IJCS_38_3_15.
2. Alan D Fleming, Sam Philip, Keith A Goatman, John A Olson, Peter F Sharp (2006) 'Automated microaneurysm detection using local contrast normalization and local vessel detection,' IEEE Trans. Med. Imag. , vol. 25, no. 9, pp. 1223–1232.
3. Meindert Niemeijer, Bram van Ginneken, Marina S A Suttorp-Schulten, Michael D Abramoff (2005) 'Automatic detection of red lesions in digital color fundus photographs', IEEE Trans. Med. Imag. , vol. 24, no. 5, pp. 584–592.
4. Simandjuntak R A, Suksmono A B, Mengko T L R, Sovani I (2005) 'Development of computer-aided diagnosis system for early diabetic retinopathy based on microaneurysms detection from retinal images', proceedings of the 7th International workshop on Enterprise networking and Computing in Health Care Industry, pp. 364-367.
5. Thomas Walter, Pascale Massin, Ali Erginary, Ricahrd Ordonez, Clotilde Jeulin, Jean-Claude Klein (2007) 'Automatic detection of microaneurysms in color fundus images' International Journal of Medical Image Analysis, pp. 555-566.
6. Usman Akram M, Shehzad Khalid, Shoab A Khan (2012) 'Identification and classification of microaneurysms for early detection of diabetic retinopathy', The Journal of the Pattern Recognition Society, pp. 1-11
7. Wong Li Yun, Rajendra Acharya, Venkatesh Y V, Carolie Chee, Lim Choo Min, E Y K Ng (2008) ' Identification of different stages of diabetic retinopathy using retinal optical images', International Journal of Information Sciences -178, pp. 106-121.
8. Jayanthi D, Devi N, SwarnaParvathi S (2010) 'Automatic diagnosis of retinal diseases from color retinal images', International Journal of Computer Science and Information Security, vol-7, No-1, pp . 234-238.
9. Priya R, Aruna P (2012) 'SVM and Neural Network based Diagnosis of Diabetic Retinopathy', International Journal of Computer Applications (0975 – 8887) Volume 41– No. 1, pp. 6-12.
10. QI Quan, ZHAO Qing-Zhan, DENG Hong-tao (2011) 'Location of Microaneurysms on Diabetic Retinopathy Images Based on Extraction of Connection Components', Proceedings of the International Conference on Compute and Management (CAMAN), pp. 1-4.
11. Neera Singh, Ramesh Chandra Tripathi (2010), 'Automated Early Detection of Diabetic Retinopathy Using Image Analysis Techniques', International Journal of Computer Applications (0975-8887), volume 8-No. 2.
12. Gonzalez and, R. C. and R. E. Woods, 2002. Digital image Processing. Prentice Hall Upper Saddle River, NJ.
13. Vapnik. V, Statistical learning theory Wiley?, New York, 1998.
14. Akara Sopharak, Matthew Dailey N. , Bunyarit Uyyanonvara, Sarah Barman, Williamson, Tom, Nwe, Khine Thet and Moe, Yin Aye (2010) 'Machine learning approach to automatic exudate detection in retinal images from diabetic patients', Journal of Modern Optics, 57(2):124-135.
15. Chih-Wei Hsu and Chih-Jen Lin (2002) 'A Comparison of Methods for Multiclass Support Vector Machines', IEEE Transactions on Neural Networks, Vol. 13, No. 2, March 2002.
16. Durgesh K. Srivastava and Lekha Bhambhu (2009), "Data Classification using Support Vector Machine", Journal of Theoretical and Applied Information Technology, Vol. 12, No. 1.

Diabetic Retinopathy (dr) Microaneurysms Morphology Support Vector Machine.