SUMMARY
Diabetic Retinopathy is a diabetes complication that usually results in abnormalities in the retinal blood vessels of the eye, resulting in blurry vision, including blurry vision and blindness. Automatic segmentation of blood vessels in retinal images can detect abnormalities in these blood vessels, actually resulting in faster and more accurate segmentation results. The paper proposed an automatic blood vessel segmentation method that combined Otsu Thresholding with image enhancement techniques, including Contrast Limited Adaptive Histogram Equalization (CLAHE) and Top-hat transformation for the retinal image. The retinal image data used in the study were the Digital Retinal Images for Vessel Extraction (DRIVE) dataset generated by the fundus camera. The CLAHE and Top-hat transformation methods were used to increase the contrast of the retinal image and reduce noise so that blood vessels could be highlighted appropriately and the segmentation process could be facilitated. Otsu Thresholding was used to distinguish between blood vessel pixels and background pixels. The performance evaluation measures of the methods used are accuracy, sensitivity, and specificity. The DRIVE dataset's study results showed that the average accuracy, sensitivity, and specificity values were 94.7%, 72.28%, and 96.87%, respectively, indicating that the proposed method was successful through blood vessels segmentation retinal images, especially for thick blood vessels.