SightWise – AI Smart Glasses for Visually Impaired

Key Highlights

• Developed a complete AI-powered smart glasses system for visually impaired individuals integrating YOLOv8-based indoor and outdoor object detection, achieving real-time inference on edge hardware.
• Built a Pakistani currency recognition module with 99.9% accuracy using a custom-trained YOLOv8 model, and Tesseract OCR for real-time text reading from documents and signage.
• Implemented offline GPS navigation using gpsd and OpenRouteService with live location sharing via Firebase, and a fully voice-controlled interface using Vosk STT and pyttsx3 TTS.
• Optimized and deployed all AI modules on Raspberry Pi 4B using TFLite INT8 quantized models, achieving real-time edge inference within the strict power constraints of a wearable form factor.
• Designed the hardware enclosure to fit within standard eyeglasses frames, integrating Raspberry Pi Camera Module 3, speaker, microphone, and GPS antenna into a functional wearable device.
• Conducted usability testing with visually impaired users, iterating on voice command vocabulary and audio feedback patterns based on real-world accessibility evaluations.