Detection of blood vessels in retinal images based on top-hat transform: article / Syurga Fathonah Aris @ Azis

This paper is proposed to detect a blood vessel in retinal images by improving the previous method called a local entropy thresholding. The system is test by using the sample from DRIVE and STARE database and is run by using MATLAB R2011b. The first step is done by extracting the green channel of RBG image since it gives better contras for the retinal images. Next, the retinal image is enhanced by morphological transformation called opening by reconstruction. This basically remove small object thus, clearing the image. Next, Top-Hat transform is applied to the retinal image. This transform is useful for uncovering detail which is rendered invisible shading or illumination over the image. After that, the step is furthered by a mask generation and match filter. The process is then followed by applying a local entropy thresholding and length filtering for blood vessel extraction. The performance of the result is determined by calculating a sensitivity and accuracy which is compared with existing hand-labelled results from DRIVE and STARE database. The average accuracy and sensitivity for proposed method is 0.89 and 0.71.