Nearly 5% of the world’s population is said to be hearing impaired, this creates a major problem for the communication with the deaf and the dumb, specially abled persons. To decrease the communication gap between hearing impaired community and the normal persons, we have designed a Sign Language Recognition System. Our application allows users to show a sign on a webcam and that sign gets converted to its respective alphabet and displayed on the screen.
- Detecting a sign and displaying the corresponding alphabets from A to Z ( Excluding J and Z)
- Detecting a sign indicated by user on a live feed and displaying corresponding alphabet
- Forming a word/sentence from the individual signs shown by user on a live webcam and displaying that word on a screen
- Recording and storing a video of user showing signs on a webcam with its respective results in a local machine
Dataset used : ASL Dataset
Colab notebook : https://colab.research.google.com/drive/1ObDUs0TZ_iXrsWTY5St536yy1ZR-cGMM?usp=sharing
Link to different Pickle files used in colab notebook : https://drive.google.com/drive/folders/18tBtniXy8X6Bg-PsSijzQalPIudTJjES?usp=sharing
Clone the project -
$ git clone https://github.com/Patrickbro13/Real-Time-Sign-Language-Recognition.git
Install all the reqirements -
$ pip install -r requirements.txt
Download the CNN model from this link and store it in your machine. Then update that model's path in model.py file
model = load_model("YOUR_MODEL_PATH")
Move to the skinMask200/code/ directory
Run the following commands -
python main.py
- Press R to start recording
- Press D to add predicted sign to previous displayed result
- Press S to add space to previous displayed result
- Press A to delete last displayed result
- Press C to clear the all displayed results
- Press T to stop recording
- Press Q to exit
- Fork this Repository.
- Clone your Fork on a different branch:
git clone -b <name-of-branch> https://github.com/Patrickbro13/Real-Time-Sign-Language-Recognition.git
- After adding any feature:
- Goto your fork and create a pull request.
- We will test your modifications and merge changes.