[Advaita-l] GoogleVisionOCR_Python

[श्रीमल्ललितालालितः]

Here is the link.

<http://goog_2023706468>
https://github.com/lalitaalaalitah/GoogleVisionOCR_Python
<https://www.google.com/url?q=https%3A%2F%2Fgithub.com%2Flalitaalaalitah%2FGoogleVisionOCR_Python&sa=D&sntz=1&usg=AFQjCNHV8wrFwqheukD9Z9SqD-LaOuuT9g>

To Coders:
Please, feel free to fork it.

To all:
I know that people who don't fear terminal, etc. will easily get it working
and develop on it.
I'll like to request proficient ones to create a docker for non-programmer
people, mostly elderly scholars who may not know how to install Python,
packages, etc.

This python script can either take an image or a folder of images and
convert image(s) to txt using Google Cloud Vision API. You may expect
accuracy of about 98% if the scan is good enough.
This script will move images to a subfolder and txt files to another for
ease of use of files.

It may help people who are working on reprints of old printed works by
taking away the burden of typing the whole book.

Copy Paste from Read me:
GoogleVisionOCR_Python

A script to use python for OCR using Google Vision API #Steps to setup

   1. Install Python 3
   2. Install dependencies python3 -m pip install google-cloud-vision Or
   pip install --upgrade google-cloud-vision
   3. Copy the script to PATH if needed
   4. Make the script executable.
   5. Follow instructions on this page :
   https://cloud.google.com/vision/docs/before-you-begin
   Create an Google Cloud Account Or Login with your Google ID
   Create a Cloud Project
   Enable billing for the project Enable Google Cloud Vision API
   Set up Authentication
   Note: You may get an offer to avail USD 300 credit for usage. Accept
   that. It may enable you to OCR without charges for a few thousand images.
   6. Call the script
   7. Follow instructions in the terminal and provide path to (file/folder)



*श्रीमल्ललितालालितः*www.lalitaalaalitah.com