Wavelet Based Contourlet Transform and Multistructure Elements Morphology by Reconstruction for Retinal Image Analysis

Abstract

Retinal fundus images are used in the diagnosis and treatment of many eye conditions, such as diabetic retinopathy and glaucoma. In a clinical examination, an ophthalmologist is capable to find out the onset of disease by taking definite features of the retinal vessels of the fundus into account. Frequently the ophthalmologist will required to select what parts of a retinal fundus image comprise vessels, so that the definite statistics such as the thickness of the vessels can be measured. However labeling all the vessels is a tedious and time consuming process. In this paper, a novel algorithm called Wavelet based Contourlet Transform (WBCT) is proposed to detect the blood vessels efficiently. The proposed Wavelet based Contourlet Transform is the combination of wavelet transform and contourlet transform used to enhance the retinal image then the image is utilized for the segmentation part. WBCT has the potential to approximate the natural images comprising contours and oscillatory patterns. The directionality features of the multistructure elements technique construct it as an effectual tool in edge detection. Therefore, morphology operators by means of multistructure elements are applied to the enhanced image in order to locate the retinal image ridges. Later, morphological operators by reconstruction eradicate the ridges not related to the vessel tree as trying to protect the thin vessels that are unaffected. To raise the efficiency of morphological operators by reconstruction, multistructure elements were applied. A Hybrid thresholding method is combined with Fast Connected Component Labeling Algorithm (FCCLA) indicates the remained ridges pertaining to vessels. The experimental results show the proposed method obtains 96% accuracy in detection of blood vessels.