RAVI - Visual Assistant
AI-powered Reading Assistant for Visually Impaired using computer vision and automated image descriptions.
- Role: Software Engineer
- Timeline: August 2022 - May 2024
- Team: RAVI Team at IIT Delhi Assistech Lab
- Technologies: Azure, JavaScript, Python, Docker
- Link: https://github.com/Laxman824/RAVI-2022-2023-
Problem
Visually impaired students struggle to access STEM education because textbooks contain diagrams, charts, and equations that screen readers can't interpret. Manual description creation is slow and expensive.
Solution
Built RAVI (Reading Assistant for Visually Impaired) - an AI system that automatically generates accurate descriptions for images in STEM documents, with crowdsourced verification for quality assurance.
Impact
- Automated descriptions for STEM images
- Crowdsourced verification workflow
- Deployed at IIT Delhi Assistech Lab
- Impacting 100+ visually impaired students
Key features
- Automatic image description generation
- STEM-specific vocabulary handling
- Mathematical equation description
- Crowdsourced verification portal
- Audio output integration
- PDF document processing
- ALT text generation
- Quality scoring system
Tech stack
- Frontend: JavaScript, HTML/CSS, Bootstrap
- Backend: Python, Flask, Azure Functions
- Ai: Azure Computer Vision, GPT-4, Custom models
- Cloud: Azure Blob Storage, Azure SQL, Docker
What K Laxman learned
- Building accessible technology solutions
- Azure Computer Vision APIs
- Crowdsourcing for quality assurance
- Working with visually impaired users
Explore more
- Home — overview, skills and a built-in AI assistant
- Experience — roles at Think360 AI (CAMS), CAMS Mutual Funds and IIT Delhi
- Projects — GenAI, LLM, RAG and full-stack builds
- Education — IIT Delhi, M.Tech & B.Tech Computer Science
- GitHub Activity — open-source contributions
- Contact / Hire me