Skip to content
/ OCR Public

Optical Character Recognition (OCR) that can take images of handwritten characters as inputs and interpret them into machine readable text.

Notifications You must be signed in to change notification settings

Jsprouse0/OCR

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

16 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

OCR

Interactive handwritten digit OCR. Draw on a full‑screen canvas and send your sketch for prediction or as a labeled training sample.

Live demo (GitHub Pages):

What it is:

  • A simple browser app (HTML/CSS/JS) that downsamples drawings to 28×28 grayscale.
  • A lightweight Python server (Flask) with JSON endpoints for predict/train.

Status:

  • UI is live; server currently returns a placeholder prediction. ANN integration is planned next.

About

Optical Character Recognition (OCR) that can take images of handwritten characters as inputs and interpret them into machine readable text.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published