Currently only has a command line interface but I am planning to improve this and add a GUI
Third year university project, use an infrared device called a 'Leap Motion' and its api in order to gather hand, joints and finger coordinates in order to train an AI model to translate British Sign Language (BSL).
-
.ipynb_checkpoints - contains all files neccessary for Jupyter Notebook to work || DO NOT ALTER.
-
model_training - .ipynb files are source code files that are opened in Jupyter Notebook.
- .ipynb_checkpoints - contains all files neccessary for Jupyter Notebook to work || DO NOT ALTER.
- data - contains hand tracking data used when developing the models
- model_testing - all the ouput files of my model testing script
- saved_models - all the different models that I have developed and saved for later use
-
scripts - where the main application scripts reside, DataExtractor.py is the driver module.
-
tests - some screenshots of graphs and confusion matrices of different models
- Leap Motion Controller is connected to computer via USB, and drivers have been installed.
- Python 2.7 installed, take note of the directory location.
- Rename the python.exe file in your Python 2.7 folder to python27.exe, if not already done.
- Python 3.9 installed.
- All python dependencies and packages installed.
- Make sure all the prerequisites are met.
- Run the command prompt (run as administrator if you encouter any problems)
- Navigate to the project's "scripts" folder using the 'cd' command. Example: cd C:\Users\winba\Desktop\TYP_SUPPLEMENTARY\scripts
- Run the DataExtractor script using python27. Example: python27 DataExtractor.py
- Follow on-screen instructions.