Retinal Image Enhancement Using Edge-based Texture Histogram Equalization


Low contrast and non-uniform illumination in retinal images hinders the process of accurate lesion detection. Edge- based Texture Histogram Equalization (ETHE) has been of significant importance with its ability to correct the contrast and illumination problems. In this paper, ETHE has been employed on retinal images to enhance the quality of the images. A new image quality model Blind\Referenceless Image Spatial Quality Evaluator (BRISQUE) which employs natural scene statistics has been used to detect the image quality. The image quality is improved by 15.125% with ETHE across four different databases. ETHE is comparable in performance with Dominant Orientation based Histogram Equalization (DOTHE), both providing similar image quality improvement. However, the average simulation time of ETHE is less than DOTHE.



Software And Hardware

• Hardware: Processor: i3 ,i5 RAM: 4GB Hard disk: 16 GB • Software: operating System : Windws2000/XP/7/8/10 Anaconda,jupyter,spyder,flask Frontend :-python Backend:- MYSQL