Hi, my name is Aditya Kumar, and I'm highly interested in contributing to projects 5 and 6, focusing on image description and content generation. I am a third-year BS Data Science student at IIT Madras. I have previous worked on the similar projects before . One was a personal project, and the other I'm currently involved with during my internship at Torch IT. At Torch IT, we are developing AI tools to assist visually impaired individuals. For our project, we can utilize open-source models like Mistral or Lama for image-to-text conversion, or closed-source models like Gemini or ChatGPT. I have implemented both open-source and closed-source models in my project. I'm also proficient in React, and I'm eager to work on the demo as well.
The project I previously worked on was a web application designed to assist visually impaired individuals. It included features such as scene description, face recognition, and optical character recognition (OCR).
Please provide any further requirements, and let me know how I can proceed with the demo and submitting my proposal.