Skip to content

Latest commit

 

History

History
48 lines (43 loc) · 3.1 KB

README.md

File metadata and controls

48 lines (43 loc) · 3.1 KB

DivyaDrishti

AI-Enhanced Learning and Interaction Assistant for Visually Impaired people at IIIT Delhi.

demo.mp4

Our revolutionary idea in the educational domain to cater to the needs of visually impaired students at IIIT Delhi by leveraging multiple facets of Computer Vision and Natural Language Processing techniques to build a Large Multi-Model (LMM) that will mitigate the challenges faced by them & bridging the gap in their educational realm by providing them with highly tailored, context- aware assistance system tailored to work in the college campus setting. This will enable them to interact seamlessly with their peers and other objects within the campus environment. Our model will be powered with facial recognition techniques, deciphering complex scenarios in a localized environment and delivering precise, actionable knowledge about the surroundings to turn daily campus navigation and social encounters into a vivid experience. VisionPulse uplifts the barrier of passive participation in classroom environments by leveraging various techniques to extract audio from lecture recordings and to create them into structured, accessible notes, which will further facilitate dynamic, content-specific Q&A sessions using Retrieval Augmented Generation (RAG). The benefits of this technology ensure that no student feels alienated due to specific barriers in their education by enhancing their class participation through information retention techniques. Besides this, our project aims to provide the user with more features like real-time obstacle detection, spatial location detection, aiding in reading emails, reading, understanding, and conveying text-based instructions in front of the user, enhancing the feasibility and easing the individual's life. VisionPulse will be able to perform actions based on voice commands and be capable of generating audio-based responses as well. Our contribution of VisionPulse to the IIIT Delhi community can act as a gateway in the realm of education for visually impaired students by creating a more inclusive, empowering, and independent educational experience for them. Our project has the potential to become one of the breakthrough contributions in the academic landscape which leverages existing tools and technology to a significant effect, which will help bridge the gaps in education for differently-abled students and create a healthy, inclusive environment where every student can thrive & unlock their full potential to scale great heights & achieve all their dreams.


Getting Started

  • Download the model archive from this link, extract the zip and place it inside this directory.

Contributors

  1. Akash Kushwaha
  2. Lakshay Kumar
  3. Manav Mittal
  4. Shreyas Kabra
  5. Tanmay Singh
  6. Utkarsh Venaik