Supporting Patients of Age-related Macular Degeneration in Malaysia using Mobile Application enabled with Object and Text Recognition

Patients contracting Age-related Macular Degeneration (AMD) disease cannot properly recognize objects or text through their central vision. After literature reviewed, there is still lack of empirical study how lightweight mobile application, operates without Internet but with object and text recognition capability can help Malaysian AMD patients to see better. This research developed a simple yet useful mobile application using Kotlin Programming and Android Studio with object and text recognition capability to generate audio speech for patients to perceive and understand better. The application yields average precision (mAP) of 42% for object recognition and 83% for text recognition. Despite lower mAP for object recognition, through Unit and Usability Testing conducted on AMD patients, the test results met the requirements and the application successfully supported them to have a better grasp of their surroundings. This research contributed a small step in relieving Malaysian AMD patients to see better and live more independently. Limitations and future improvements were also provided.