Application built for the ImageSpeak challenge at the YAMAHA AI Innovate 3.0 Hackathon held at IIT Mandi on 27th-28th April, 2024.
The challenge focuses on developing a deep learning model capable of generating descriptive captions for images, enabling users to gain meaningful insights from visual content with the aim of enhancing accessibility for individuals who are blind or visually impaired.
The participants were required to integrate the developed model into a mobile application, allowing users to capture images and receive descriptive captions in real-time.
