Fundus retinal image vessel segmentation with image processing techniques

Retinal images can be used in different areas such as human recognition and ocular fundus operations. Many common eye diseases like; Age-Related Macular Degeneration, Glaucoma, Diabetic Retinopathy and cardiovascular diseases can be diagnosed with the help of these retinal images. Unfortunately diagnosing of these abnormalities is a challenging duty due to low contrast, uneven illumination, blurred images and poor quality images. On the other hand automated detection systems that use retinal images will be highly beneficial in near future. These automated detection systems can decrease the work load of ophthalmologists and with the help of this system patients can receive accurate treatment right on time. In this project most accurate blood vessel segmentation and extraction techniques will be proposed. In this thesis we used the H-minima transform for blood vessel segmentation. The aim of this thesis was to get the high accuracy of blood vessel segmentation in retinal images. In this thesis the good result and good performance was get by using computer vision and image processing tools. We compared our result with other methods. Also for simulation result we will implement on DRIVE and STARE database.