OCR with Python

# Purpose: To make OCR on a directory containing image files, 
#          recognized texts are stored in the text files of a target directory.


Step 1 : Install tesseract for Python :

==> https://www.pyimagesearch.com/2017/07/10/using-tesseract-ocr-python/

Step 2 : Eventually install additional language packs

==> https://ocrmypdf.readthedocs.io/en/latest/languages.html


Source code for example : 

from PIL import Image
import pytesseract
import os

DirIn = 'C:/TestIn'     # Directory containing scanned pictures
DirOut = 'C:/TestOut'   # Output directory

FileList = [ f for f in os.listdir(DirIn) if os.path.isfile(os.path.join(DirIn,f)) ]

for i in range(0,len(FileList)):

inFile = FileList[i]

inFileFullPath = DirIn + '/' + FileList[i]

target = inFile.replace('.gif','.txt')

target = DirOut + '/' + target
    
outFile = open(target,'wb')

    # German text 
text = pytesseract.image_to_string(Image.open(inFileFullPath), lang='deu')

outFile.write(text.encode('utf-8'))

outFile.close()

File download : OCR.py