Extract Text From Image Using Python

 

 

We are going to use pytesseract and pillow library to work on this project!

Before you start coding, you need to complete three tasks:

1. Click on the link below and install tesseract-OCR

https://github.com/UB-Mannheim/tesseract/wiki

After you install the setup successfully, take a note of where you are saving the file because we need that path in our code.

2. Install pytesseract by using command : pip install pytesseract

3. Install pillow by using command : pip install pillow 

 

Source Code:

import pytesseract
from PIL import Image
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'
value=Image.open('logo.png')
text=pytesseract.image_to_string(value)
print("Extracted Data is: \n ", text) 

Notice that if you want to add full path, you need to add double slash (\\) instead of single slash (\) in you path

For Example: If your path looks like this: D:\Python_Program\my_Image.jpg

Then replace \ with \\

something like : D:\\Python_Program\\my_Image.jpg

Or

Add  alphabet 'r' before your string
example:     r'C:\Program Files\Tesseract-OCR\tesseract.exe'

and then you are good to go!