SUMMARY
To diagnose diabetic retinopathy is to segment the blood vessels of the retinal, but the retinal images in the DRIVE and STARE datasets have varying contrast, so the enhancement is needed to obtain a stable image contrast. In this study, image enhancement was performed using the Contrast Stretching and continued with segmentation using the Adaptive Thresholding on retinal images. The image that has been extracted with green channels will be enhanced with Contras Stretching and segmented with Adaptive Thresholding to produce a binary image of retinal blood vessels. The purpose of this study was to combine image enhancement techniques and segmentation methods to obtain valid and accurate retinal blood vessels. The test results on DRIVE were 95.68 for accuracy, 65.05% for sensitivity, and 98.56% for specificity. The test results of Adam Hoover’s ground truth on STARE were 96.13% for, 65.90% for sensitivity, and 98.48% for specificity. The test results for Valentina Kouznetsova’s ground truth on the STARE were 93.89% for accuracy, 52.15% for sensitivity, and 99.02% for specificity. The conclusion obtained is that the processing results on the DRIVE and STARE datasets are very good with respect to their accuracy and specificity values. This method still needs to be developed to be able to detect thin blood vessels with the aim of being able to improve and increase the sensitivity value obtained.