Skip to content

A program to classify doodles and alphabet drawn by the user into different classes with their corresponding confidence percentages.

License

Notifications You must be signed in to change notification settings

Mitul-Joby/Doodlifier

Repository files navigation

Doodlifier

Doodlifier is a program to classify doodles and alphabet drawn by the user into different classes with their corresponding confidence percentages.

Doodle Prediction 1

Run

  • Install tensorflow
  • Install requirements
  • Run main.py

Uses existing model and class names by default.

To customize doodles, delete files under model and update doodle.txt with reference to available.txt, and run main.py.

About

Doodlifier uses a Convolutional Neural Network to extract features, enhance them and then using softmax returns probabilities for each class label. An accuracy of roughly 95 percentage was attained.

Doodle Prediction 1

  • From doodle.txt, the required class npy files are downloaded from Google's Quickdraw datasets.

    Check available.txt for a list of available classes.

  • They are randomized to try eliminating intialization bias and classes are one hot encoded and then trained and tested.

  • Images are resized to 28x28 and preprocessed.

  • These images are passed to the model and then class probabilities are returned.

  • The model is then saved along with class names.

Doodle Mode

Doodle Prediction 1   Doodle Prediction 2   Doodle Prediction 3

Alphabet Mode

Alphabet Prediction 1   Alphabet Prediction 2   Alphabet Prediction 3

Datasets

Doodles

Refernces

To Do

  • Muliple detections with the help of YOLO
  • Better datasets for English Characters and digits
  • Add more models

About

A program to classify doodles and alphabet drawn by the user into different classes with their corresponding confidence percentages.

Resources

License

Stars

Watchers

Forks

Contributors 3

  •  
  •  
  •  

Languages