Real-time colour segmentation and autofocus in retinal images

This research is applied to the processing of retinal images. These are often corrupted with low contrast, noise, poor illumination etc. Retinal images are typically high resolution, colour data, hence there is a need to identify the important areas of the retina, through the process of segmentation. In this work, we propose a real-time colour segmentation algorithm for the extraction of the useful part of the retina. In order to quantify the quality of the segmented image, we carry out a comparison of image focus techniques. The results verify the robust-performance of the algorithm