Skip to content

A application that detects handwritten digits using deep learning

License

Notifications You must be signed in to change notification settings

douglasramos/handwritten-digits-detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Project

This project, still in development, is based on the scripts (Python 2) made in the book neuralnetworksanddeeplearning.com by Michael Nielsen, and also on the Michael Daniel Dobrzanski's scripts, that is the same as the book by in Python 3. The aim of this project is to reproduce and evolve what was done by the aforementioned works, achieving better performance and accuracy, and making it a software-product, with user interface and new functionalities.

Road Map

  • Finish the basic neural network

  • Improve the accuracy with some other techniques

  • Read the digit from a generic photo

  • Read a sequence of digits from a generic photo

  • Extend to the alphabet

  • Build a web or desktop user interface

License

Copyright © 2019 Douglas Ramos

Distributed under the MIT License, with due credit to the work on which this project was based.

About

A application that detects handwritten digits using deep learning

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages