Abstract
In this article, a Combination of Fuzzy logic and Texture features based segmentation approach for retinal blood vessel segmentation is proposed. The proposed approach employs a new methodology for segmenting the blood vessels from the retinal images more effectively. The overall process is carried out in five steps. The first step is to pre-process the image in order to remove the presence of noise in it and to convert the color image to grey scale image. Second step is the border detection process where the of the blood vessels is are moved by a border detection algorithm. Third step is the texture features are extracted from the detected border and then these features are given as input towards the Improved Fuzzy C Means clustering (IFCM) method in order to produce the membership function. Fourth step is the defuzzification process in which the outputs of the inference obtained for each pixel is combined to a final segmented output which provides a segmented foreground against the background. Final step is the Post-processing process where the unwanted pixels are filled or removed. Our proposed algorithm is tested over 180 images in order to analyse its efficiency. From the experimental results, it has been observed that the proposed segmentation approach provides better segmentation accuracy of 97.8 % in segmenting Retinal blood vessels.