Glaucoma Detection from Retinal Fundus Images
I co-authored undergraduate work on glaucoma screening from retinal fundus images using optic-disc and optic-cup segmentation, cup-to-disc ratio measurement, and SVM classification.
Result
ICCSP 2020 paper reporting 86% F1 for SVM-based glaucoma classification
We developed an image-processing pipeline with threshold-based optic-disc segmentation and modified region growing for optic-cup segmentation, followed by cup-to-disc ratio measurement and SVM classification.
On the Drishti-GS dataset, we reported an F1 score of 86% for classification. We presented the work at ICCSP 2020 and published it on IEEE Xplore.
MATLABImage ProcessingSVM