emnikhil/Sign-Language-To-Text-Conversion
Sign Language to Text Conversion is a real-time system that uses a camera to capture hand gestures and translates them into text, words, and sentences using Computer Vision and Machine Learning.
# Technical Summary Built on a CNN architecture with preprocessing pipeline using OpenCV (grayscale conversion, Gaussian blur, adaptive thresholding), the system trains on a custom fingerspelling dataset resized to 128×128 pixels and achieves 98% accuracy on 26-letter American Sign Language recognition. The model uses convolutional layers with max-pooling for feature extraction, fully connected layers for classification, and SoftMax normalization with cross-entropy loss optimization via TensorFlow. A GUI frontend enables real-time gesture-to-text conversion by chaining individual letter predictions into complete words for accessibility communication.
348 stars. No commits in the last 6 months.
Stars
348
Forks
127
Language
Python
License
MIT
Category
Last pushed
May 21, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/emnikhil/Sign-Language-To-Text-Conversion"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
Devansh-47/Sign-Language-To-Text-and-Speech-Conversion
This is a python application which converts american sign language into text and speech which...
shekit/alexa-sign-language-translator
A project to make Amazon Echo respond to sign language using your webcam
arch-ith/voice_to_signLanguage
Voice to Sign Language Conversion
bishal7679/ASL-Transformer
A user-friendly application for converting either audio or text into sign language animations.
RhythmusByte/Sign-Language-to-Speech
Real-time ASL interpreter using OpenCV and TensorFlow/Keras for hand gesture recognition....