Python - Image to text enclosed in pentagon shape pytesseract

Question

I am trying to ready Energy Efficiency Rating from EPC certificate using python. Usually EPC certificate comes in PDF format. I have converted PDF into image already and using pytesseract to get text from image. However I am not getting expected results.

Sample Image:

Expected output: Current rating : 79, Potential rating : 79

What I have tried so far:

from pdf2image import convert_from_path
import pytesseract
from PIL import Image

pages = convert_from_path(r'my_file.pdf', 500)
img =pages[0].save(r'F:\Freelancer\EPC rating\fwdepcs\out.jpg', 'JPEG')
text = pytesseract.image_to_string(Image.open(r'F:\Freelancer\EPC rating\fwdepcs\out.jpg'))

However text does not capture 79.

I also tried cv2 pattern matching and shape detection, but those not worked for other reasons.

Answer 1

You say that you have convert this pdf to image file.

Use PIL(.crop()) or opencv to crop picture.And crop it like this:

And use PIL Image.convert("1") ,maybe tesseract can catch this number. If not,I think you can use jTessBoxEditor to train tesseract.