https://entorb.net//wiki/index.php?action=history&feed=atom&title=Python_-_OCR 2026-05-06T10:23:33Z Revision history for this page on the wiki MediaWiki 1.43.1 https://entorb.net//wiki/index.php?title=Python_-_OCR&diff=4844&oldid=prev 2024-10-30T20:21:37Z

<p></p> <p><b>New page</b></p><div>[[Category:Coding]][[Category:Python]]<br /> ==Optical Character Recognition (OCR) via pytesseract and Tesseract==<br /> import os<br /> import cv2 # c:\Python\Scripts\pip install opencv-python<br /> <br /> import pytesseract<br /> # Requirements pytesseract<br /> # 1. Tesseract https://github.com/tesseract-ocr/tesseract/wiki#windows<br /> # -&gt; e:\win\progs\Tesseract-OCR\tesseract.exe<br /> # Windows Path muss e:\win\progs\Tesseract-OCR\ enthalten<br /> # Windows Umgebungs Variable TESSDATA_PREFIX -&gt; e:\win\progs\Tesseract-OCR\<br /> #<br /> # 2. pytesseract<br /> # c:\Python\Scripts\pip install pillow<br /> # c:\Python\Scripts\pip install pytesseract<br /> <br /> # Read Input file <br /> image = cv2.imread(&#039;image.png&#039;)<br /> # export temp file<br /> filename = &quot;tmp/{}.png&quot;.format(os.getpid()) # mkdir tmp first!<br /> cv2.imwrite(filename, image)<br /> text = &quot;&quot;<br /> try:<br /> # character whitelist: digits only <br /> text = pytesseract.image_to_string(Image.open(filename), config=&#039;digits&#039;, lang=&quot;eng&quot;)<br /> except: # attention: wildcard exception<br /> print(&quot;ERROR Unexpected exception:&quot;, sys.exc_info()[0])<br /> text = &quot;&quot;<br /> os.remove(filename)<br /> print(text)<br /> cv2.waitKey(0)</div>

Torben