Skip to content

README.md

Latest commit

 

History

History
36 lines (21 loc) · 668 Bytes

README.md

File metadata and controls

36 lines (21 loc) · 668 Bytes

Meme OCR

This is an optical character recognition (OCR) tool using Tesseract specifically for internet meme images.

Requirement

  • Install the tesseract executable by this tutorial
  • Install Python OpenCV package by:
$ sudo pip3 install opencv-python

Usage

  1. Prepare your meme image (e.g. /path/to/your/some-crazy-meme.jpg).
  2. Just run:
$ ./main.py /path/to/your/some-crazy-meme.jpg

And the recognized texts will be printed in the stdout.

Examples

$ ./main.py ./examples/socially-awkward-penguin.jpg