https://github.com/techytushar/sign-language-recognizer
Using CNN to recognize hang signs language
https://github.com/techytushar/sign-language-recognizer
Last synced: 10 months ago
JSON representation
Using CNN to recognize hang signs language
- Host: GitHub
- URL: https://github.com/techytushar/sign-language-recognizer
- Owner: techytushar
- Created: 2019-02-03T06:49:57.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2019-02-03T17:17:54.000Z (over 7 years ago)
- Last Synced: 2025-02-24T16:52:22.396Z (over 1 year ago)
- Language: Jupyter Notebook
- Homepage:
- Size: 13.7 MB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Sign Language Recognizer
A simple deep learning project which uses CNNs to recognize the digits from the hand gesture.
**Demo Video:** https://youtu.be/exHGP5kIlDA
## Project Details
* **API :** Keras
* **Backend:** Tensorflow
* **Dataset:** https://github.com/ardamavi/Sign-Language-Digits-Dataset + Some custom images
* **Model Architecture:** Conv->MaxPool->Conv->MaxPool->Flatten->Dense(512)->Dense(128)->Output(10)
* **Python Version:** >=3.6
## How to use
* Install the dependencies using:
```bash
pip3 install -r requirements.txt
```
* (Optional) Prepare you custom dataset. Run the script and press the number key for which you want to save the image.
```bash
python3 capture_digits.py
```
* Train the model using:
```bash
python3 train_model.py
```
* Run the digits recognizer using:
```bash
python3 recognize.py
```