Enhancing detection of retinal blood vessels by combined approach of DWT, Tyler Coye and Gamma correction

Abstract

Retinal imaging plays the most significant roles among all the medical imaging technology, because of its ability to derive various features that is related to various eye diseases. Thus, precise extraction is highly required for the blood vessels that lead to accurate identification of the diseases. Because of some instabilities in the retinal images such as noise, non-uniform illumination etc. it may motivate towards a false detection. This paper suggests an automated method to extract the blood vessels from fundus by integrating discrete wavelet transform (DWT) with Tyler Coye algorithm. Furthermore, in the retinal blood vessel segmentation methods the most vital step is to enhance the contrast. The authenticity of the segmentation is purely subjected to the uniformity of the contrast over the image. Thus, an illumination normalization technique known as Gamma correction is also utilized for the contrast enhancement. Three different types of experiments are carried out: original Tyler Coye algorithm, DWT with different wavelet filters integrated with Tyler Coye, and Gamma correction normalization applied to the integrated model. The approaches are tested with DRIVE dataset. The performance of the normalization-integrated model is found superior to the other two approaches.