https://github.com/ozep/asl-interpreter

Hand tracking module empowered by OpenCV and MediaPy, customized to detect letters via sign language (ASL)
https://github.com/ozep/asl-interpreter

mediapy opencv-python pycharm python

Last synced: 5 days ago
JSON representation

Hand tracking module empowered by OpenCV and MediaPy, customized to detect letters via sign language (ASL)

• Host: GitHub
• URL: https://github.com/ozep/asl-interpreter
• Owner: oZep
• License: mit
• Created: 2023-12-24T01:20:10.000Z (11 months ago)
• Default Branch: main
• Last Pushed: 2023-12-29T03:38:50.000Z (10 months ago)
• Last Synced: 2024-10-16T22:07:27.706Z (20 days ago)
• Topics: mediapy, opencv-python, pycharm, python
• Language: Python
• Homepage:
• Size: 70.3 KB
• Stars: 1
• Watchers: 2
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: MIT-LICENSE.txt

Awesome Lists containing this project

README

        
# HandTracking (ASL Interpreter)

[23/12/2023] - Present

- Using OpenCV and MediaPy

https://github.com/oZep/HandTracking/assets/97713154/899c24fd-c1d9-43c3-a08b-800a034008db

# Main Idea



![image](https://github.com/oZep/HandTracking/assets/97713154/a7412c7e-72fe-49c8-8981-b5f996b71e01)

This module will help interpret these symbols and enable beginners to understand ASL instantly. 

After the main ASL interpreter module is complete, I will take this project into the real world and decode ASL via Audio connected to a headset

## Progress

- Main Landmark Decoding Logic Complete

- Finished assigning Alphabet Landmarks it's correct POI (points of interest) and set up a way to have orientation of the hand be considered (ORT)

- Testing all characters, I found the program has issues distingishing between gestures that are very similar to eachother but very by lenght between landmarks, especially with C and O. I think calculating the distance between all hand landmarks will be the next step in making the system more precise.