Skip to content

Kurtis24/Handwritten-Digit-Recongizer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Handwriting Digit Recognizer

Overview

This project is a simple yet effective tool that recognizes single handwritten numbers with an accuracy rate of 93%. Users can write any number on a 28x28 virtual whiteboard, and the recognizer provides a prediction within 3 seconds.

How It Works

The recognizer utilizes a basic Convolutional Neural Network (CNN) trained on handwritten digit data. By analyzing 28 pixels line by line, the model predicts the number based on the patterns formed by the lines. Key libraries such as NumPy and TensorFlow are employed for data processing and model computations.

About

My projects :D

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages