Skip to content

NIAEFEUP/hand-painter

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

125 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Folder Structure

hand-painter

Contains the code to run the application. The application uses the MediaPipe library to track the hand and the OpenCV library to draw on the screen. There are two modes:

  • paint mode: the user(s) can draw on the screen using the hand(s).
  • challenge mode: the user is challenged to draw the object of a random word using the hand and the application will find the similarity between the drawing and the chosen word.

To set up the application, read the README file in the hand-painter folder.

cnn (Conventual Neural Network)

Contains the code to train the CNN model. The model is used to predict the class of a drawing. It's trained on the dataset provided by the QuickDraw project.

About

This model utilizes MediaPipe's hand tracking functions to get hand landmarks(reference points) that enable the user to actually draw stuff on the screen.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages