Regular examination of retina in diabetic patients can assist in the early detection, diagnosis and management of diabetic retinopathy as it continues to be one of the major causes of blindness globally. The manual detection of the retinal vessels is a very tedious and time consuming task. Although automatic vessel detection has been helpful in achieving speed, it has been challenging due to some complexities such as varying width of retinal vessels from very large to very small, low contrast of thin vessels with respect to background and noise due non-homogeneous illumination in the retinal images. In order to address these problems, this book presents different unsupervised texture-based segmentation techniques for the robust detection of large and thin retinal vessels in timely efficient manner. The characterization of the detected vessels using different tortuosity measures is also presented in this book.