Loading repository data…
ChirayuDodiya / repository
Sign Language to Text Converter is a Python-based application that recognizes hand gestures using computer vision and converts them into text in real time. It leverages OpenCV, MediaPipe, and a trained ML model to assist communication for speech-impaired users.
A transparent discovery signal based on current public GitHub metadata.
This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
The Sign Language to Text Converter for Speech Impaired is a project aimed at translating Sign Language into written text. It uses machine learning and computer vision to understand sign language and provide accurate translations, making communication more accessible and easy for people with hearing and speech impairments.
We have mainly used Python and some of its libraries and tools to build this project. Some of these are:
🟡 cvzone: Used to access the camera to capture hand gestures, including the built-in HandDetector library for hand detection.
🔢 Numpy: Used for model predictions, specifically for predicting different hand signs and the letters used.
🖐 Mediapipe: A cross-platform framework developed by Google for processing video and multimedia. It provides advanced capabilities for hand tracking and gesture recognition, making it ideal for real-time Sign Language recognition.
🔍 OpenCV: An open-source computer vision and machine learning library that provides tools for image and video processing, essential for capturing and manipulating frames from a webcam.
🧠 TensorFlow: An open-source machine learning framework developed by Google, widely used for building and training machine learning models. In this project, TensorFlow runs the neural network model that recognizes Sign Language gestures.
🤖 Teachable Machine: A user-friendly web tool that allows anyone to create machine learning models without coding, designed for tasks like image classification and pose detection.
Selected from shared topics, language and repository description—not editorial ratings.
dgovor /
Neural Network that is able to translate any sign language into text.
65/100 healthSign.AI is a Sign Language Recognition application built on top of MediaPipe and uses Computer Vision to Recognize Hand Signs from a users video capture device. SignAI is accurate and also has the capability to autocorrect words and phrase sentences using GingerIt. Sign.AI also provides Hindi Translation for predictions using Argostranslate.
68/100 health
git clone https://github.com/ChirayuDodiya/Sign-Language-To-Text-Convertor-for-Speech-Impaired
pip install -r requirements.txt
The process of developing the Sign Language to Text Converter involves three main steps: data collection, model training, and testing. Here's how each step works:
collect.pycollect.py script.collect.py..h5 format).test.pytest.py script.In this section, we provide a demonstration of the Sign Language to Text Converter. Below are the steps to showcase how the application works, along with visual aids.
Start the Application:
test.py script to initiate the application.User Interface:
Perform Hand Signs:
Watch the following video to see the Sign Language to Text Converter in action:
We welcome feedback! If you have any suggestions or issues, please open an issue on our GitHub repository.
RhythmusByte /
Real-time ASL interpreter using OpenCV and TensorFlow/Keras for hand gesture recognition. Features custom hand tracking, image preprocessing, and gesture classification to translate American Sign Language into text and speech output. Built with accessibility in mind.
59/100 healthSohamPrajapati /
The Sign Language Detector and Translator is an innovative web application that leverages the power of machine learning, Flask Python, and web development to bridge the communication gap between the Deaf and Hard of Hearing community and the hearing world.
57/100 healthNasimBahadur /
Bangla sign recognition system is developed based on a deep learning approach named LSTM. As a feature extractor, Mediapipe Holistic is also used in this system. This system is able to work on static and dynamic both types of gestures and recognize simple or complex signs.
56/100 healthshukur-alom /
it able to detect ten type USA sign language. which is Okay, Peace, Thumbs up, Thumbs down, Call me, Stop, I Love You, Hello, No, Smile.
41/100 health