Performance analysis of diabetic retinopathy using diverse image enhancement techniques
Main Article Content
Article Sidebar
Abstract
Abstract
Most retinal diseases can be manifested by retinal fundus images. However, the fundus image quality is not adequate for diagnosing retinal disease such as diabetic retinopathy (DR) due to color distortion, low contrast, uneven illumination, and blurring. Therefore, there is a need for enhancing the images by applying various enhancement techniques. This paper implements diverse methods for image enhancement such as wiener filter, median filter, Contrast Stretching, Histogram Equalization, Contrast adjustment, Morphological top hat filter, morphological bottom hat filter, Adaptive Histogram Equalization, Contrast limited Adaptive histogram Equalization (CLAHE) on retinal images. The performance has been evaluated on DRIVE and STARE dataset which includes Peak Signal to Noise Ratio, Structural similarity Index, Mean Square Error, Maximum difference, Normalized cross-correlation, structural Content, Normalized absolute error, Average difference, and Entropy of the images. It is concluded that wiener filter performs best in noise removal techniques. However the contrast of the images can be improved by CLAHE. Moreover Morphological operators are used for effective segmentation of blood vessels.