Computer Vision
Sign Language to Text Converter
Real-time computer vision application capable of recognizing sign language gestures through live webcam input and converting them into text.
- Python
- OpenCV
- CNN
- Computer Vision
Overview
A real-time computer vision application that recognizes sign language gestures from live webcam input and converts them into text.
Solution
A Python pipeline that captures webcam frames, preprocesses and extracts features from them, classifies gestures with a CNN, and renders the recognized characters as text.
Architecture
- Capture
- OpenCV webcam input
- Processing
- Image preprocessing + feature extraction
- Model
- CNN classifier
- Output
- Real-time text conversion
Current state
Runs locally as a desktop application; no public deployment or repository link is available.