top of page
Search

Project 4d - Tesseract (OCR) with CUDA support

  • Writer: James Canova
    James Canova
  • Sep 9, 2021
  • 1 min read

Project start: 5 January 2022

Project finish: 6 January 2022


Last updated: 13 August 2022


Objective: Installation of Tesseract (pytesseract) for optical character recognition (OCR) with CUDA support in VEnv. This will be used in project 6 for reading license plates


I am not yet sure if Tesseract is available with CUDA support. I will provide an update when I find out.



outside VEnv:


cd $HOME



sudo apt-get install libleptonica-dev
sudo apt-get install tesseract-ocr 
sudo apt-get install libtesseract-dev


I added this 4 January 2022 to .bashrc:



export 
"/usr/local/bin:/usr/bin:/bin:/usr/sbin:/sbin:~/home/james/Public/Projects/myPython36VEnv/bin"



Inside VEnv:



(myPython36VEnv) james@myB01:~/Public/Projects$ pip3 install -U pytesseract
->Successfully installed pytesseract-0.3.8



In jupyter-notebook:


import pytesseract as pyOCR
print(pyOCR.__version__)
->0.3.8




If you have any problems or need clarification please contact me: jscanova@gmail.com



 
 
 

Recent Posts

See All
Introduction

I became interested in artificial intelligence in mid 2021 after watching a documentary on this subject. In particular, I'm interested in...

 
 
 
References

1.Rashid, Tariq, Make Your Own Neural Network , Amazon , 2016 2.Portilla, Jose, "Python for Computer Vision with OpenCV and Deep...

 
 
 
Status of Projects

Last updated: 30 March 2024 Project 0: Read this to get a very basic understating on machine learning and neural networks. Project 1:...

 
 
 

Comments

Couldn’t Load Comments
It looks like there was a technical problem. Try reconnecting or refreshing the page.
Post: Blog posts

©2021 by My Machine Learning Blog. Proudly created with Wix.com

bottom of page