Ocular Disease Recognition Using TinyML for Efficient Android Implementation

Ocular diseases represent a significant global health concern, with early and accurate diagnosis playing a crucial role in preventing vision loss. In this study, we present a pioneering approach to the classification of ocular diseases using TinyML, a cutting-edge technology that leverages the power of machine learning on resource-constrained devices. Our work addresses the pressing need for efficient, real-time, and cost-effective solutions in ophthalmology. Our study showcases the comparison of three TinyML CNN models trained to detect eye diseases and tested on an Android implementation, offering a reliable and accessible tool, with accuracies of over 98,83%, for the early detection and management of ocular diseases, ultimately improving patient outcomes and reducing the global burden of vision impairment.