Detail Preserving Retinal Image Enhancement

Enhancement of retinal images supports both manual examination of anomalies by medical experts and also automatic segmentation, registration, and classification tasks. All three kinds of enhancements, brightness adjustment, contrast enhancement and noise reduction, needs to target different tissues in a different way. For example, contrast enhancement has to be applied only on retinal tissues and anomalies otherwise contrast of noise may also increase. Noise reduction whether applied as pre-processing or post processing, also reduces details in the image such as fine blood vessels. We propose a total variation based retinal image enhancement method, which accomplish brightness adjustment, contrast enhancement and noise reduction simultaneously while preserving details. Proposed method produces satisfactory results for the DRIVE database in colour and grayscale modes.