• Mamtha Mohan
• Tejaswini G M

Medical sciences has a greater importance with regards to medical analysis ,which helps diagnosing many diseases of human fraternity. Diabetic retinopathy (DR) is one of the most frequently caused disease which leads to blindness and vision loss in diabetic patients. The earlier it is detected, the better the chance that it can be effectively treated and further vision loss can be prevented. This condition increases the importance of automated detection of the disease. This work focuses on distinguishing between diabetic retinopathy (DR) and normal fundus images by analyzing the texture of the retinal background. Local Binary Patterns (LBP) are used as texture descriptors. They are the powerful grey-scale texture descriptors that is commonly used because of its computation simplicity. Local Binary Pattern is based on looking at the local variations around each pixel, and assigning labels to different local patterns and the labels are evaluated and used in the classification stage. Diabetic Retinopathy is detected by the presence of microaneurysms and exudates in the color fundus image of the eye. The work examines the analyzing capabilities in the texture of color fundus images to differentiate between diseased and healthy images. Aiming this, the performance of Local Binary Patterns as a texture descriptor for retinal images has been explored. The performance of the proposed algorithm is analyzed using parameters like sensitivity, specificity, accuracy and severity. A multiclass SVM is deployed to classify the images.

Color fundus images, Diabetic Retinopathy, Medical analysis, Microaneurysms, Local Binary Pattern

"An approach to detect Diabetic disease by Texture Analysis of Fundus Images", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 3, page no.326-331, March-2019, Available :http://www.jetir.org/papers/JETIRAL06068.pdf

"An approach to detect Diabetic disease by Texture Analysis of Fundus Images", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 3, page no. pp326-331, March-2019, Available at : http://www.jetir.org/papers/JETIRAL06068.pdf