AIRA: A Virtual Assistant for the Visually Impaired
Visually Impaired Assistance, Voice Assistant, Natural Language Processing (NLP), Computer Vision, Object Detection, Text Recognition, Scene Description, Real-Time Assistive Technology
• designed and developed a mobile application that empowers visually impaired users with real-time assistance.
• implemented real-time object detection using the smartphone camera to identify and label surrounding items.
• enabled accurate optical character recognition (OCR) for reading both printed and handwritten text.
• generated meaningful scene descriptions using AI-based image captioning techniques
Video Understanding Using Temporal Action
Localization
Temporal Action Localization,Transformers,Optical Flow,Video Understanding ,Action Recognition.
Emotion Detection and Empathetic Response Generation using Generative AI and NLP
Emotion Recognition , Precision Analysis , Support Vector
Machine , Logistic Regression , Random Forest , XGBoost , Decision Tree
•Developed an Emotion Classification Model:
Created system capable of identifying human emotions (joy, anger, sadness, etc.) from short texts using generative ai techniques
•Utilize Effective Feature Engineering:
Applied NLP preprocessing techniques (tokenization, lemmatization, TF-IDF) to convert raw text into meaningful features.