Assessment of Fundus Images for Retinal Abnormality Screening-A Study

摘要

Screening of eye is essential to identify a range of retinal irregularities, and Fundus Imaging (FI) is one of the techniques commonly used by the ophthalmologist to record and evaluate the retinal abnormalities. Manual appraisal of FI is time-consuming, and hence, a computer-based methodology is always preferred. This work aims to develop a system to examine the retinal abnormality with the help of FI pictures. This work employs a hybrid processing scheme to enhance and extract the FI in order to extract and assess the optic-disc section. In this work, enhancement is done with firefly algorithm and Kapur's thresholding, and the extraction is implemented with level set technique. All these testing are put into practice with MATLAB software using the benchmark Rim-One FI database, and the results of this study confirmed that the anticipated technique offered enhanced outcome in extracting the disc section from the RGB scaled FI.