A Hybrid Model of Contrast Enhancement with Particle Swarm Optimization for Diabetic Retinopathy (S/O 14404)

• Main Authors: Harun, Nor Hazlyna, Yusof, Yuhanis, Abu Bakar, Juhaida, Osman, Muhammad Khusairi, Embong, Zunaina
• Format: Monograph
• Language: English
• Published: UUM 2023
• Subjects: QA75 Electronic computers. Computer science
• Online Access: https://repo.uum.edu.my/id/eprint/30575/1/14404.pdf; https://repo.uum.edu.my/id/eprint/30575/

Identifying features of Diabetic Retinopathy (DR) based on fundus image is currently conducted through eye exam by an ophthalmologist. Tracking DR progression manually is time consuming and error-prone. As the technology offered in Industrial Revolution (IR) 4.0, namely Artificial Intelligence, is shown to reduce medical errors, this study proposes an image enhancement algorithm based on hybrid of Contrast Enhancement (CE) and Particle Swarm Optimization (PSO). The proposed method incorporate contrast adjustment on bright and dark region of LAB color space where the bright and dark region initially segmented using K-mean PSO. 100 retinal fundus images is used for training and testing purpose. The proposed method undergo qualitative and quantitative evaluation. Comparison with several method also conducted. The result indicates that performance of proposed method enhancement is more acceptable as compare to other resultant image. Further experiment is needed to handle the drawback occurred.