https://github.com/chekoduadarsh/image-to-text-converter-ocr

🖼️ ➡️ 📜
https://github.com/chekoduadarsh/image-to-text-converter-ocr

api google google-vision google-vision-api ocr ocr-recognition opencv python3 tesseract tesseract-ocr

Last synced: 14 days ago
JSON representation

🖼️ ➡️ 📜

• Host: GitHub
• URL: https://github.com/chekoduadarsh/image-to-text-converter-ocr
• Owner: chekoduadarsh
• Created: 2018-03-06T16:32:44.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2021-03-02T12:05:11.000Z (over 3 years ago)
• Last Synced: 2024-10-04T15:49:03.511Z (about 1 month ago)
• Topics: api, google, google-vision, google-vision-api, ocr, ocr-recognition, opencv, python3, tesseract, tesseract-ocr
• Language: Python
• Homepage:
• Size: 203 KB
• Stars: 15
• Watchers: 6
• Forks: 7
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Image to Text Converter-OCR  (python 3.x)

The attached code is a simple code which will convert Image into text using tesseract and google vision api.

# Tesseract OCR

Tesseract is an optical chraracter recognition library used in python but its efficiency is very low compared with Google vision API but we can increase contrast or create binary image using opencv to enhance the output.

to install tesseract:-

  https://www.linux.com/blog/using-tesseract-ubuntu

  

 In the given code i have applied binary image convertion to get better output

Required libraries

  OPEN CV

  TESSERACT OCR

  numpy

  

# GOOGLE VISION API

This is the most advanced API availible for optical character recognition and it offers other services like face recognition,  logo, and landmark detection, etc. 

HOW TO USE IT:-

  1. Create a project in google console and add vision api to it.

  2. In this project go to credentials and create Service account keys

  3. Download Service account keys in .json format 

  4. Give its path in code.

  5. RUN