This project is divided into two parts:

• Detection
• Recognition

Execute the air-handwriting-detection-and-recognnition.ipynb with color_selector.py in the same folder if you are running code on jupyter notebook or VS code or any local host machine with replacement of path of dataset and last_frame.png to where you have saved your dataset and last_frame.png.

If execution is done using Google Colab; Execute the detection.py with color_selector.py in the same folder of code using VS Code or prefered python editor and OCR.ipynb in google colab by uploading last_frame.png into your google drive and replacing the path of both dataset and last_frame.png.

Initially Training is set to True, Changing it to false will use the trained model but initially you have to train the model.

A-Z Dataset

This image shows a histogram plot of complete dataset, representing number of entries of each label.

Ploting Images:

• Training Data
• Testing Data (Shows the predicted label)

test1 and train1 are the output of the ADAM while test2 and train2 are the output of RMSProp

• Abhishek chaudhary
• Khushi Agrawal
• Prabhat Kumar