Help Pytesseract OCR shipping labels

[Help] Pytesseract OCR shipping labels - Printable Version

+- Hack Forums (https://hackforums.net)
+-- Forum: Tech (https://hackforums.net/forumdisplay.php?fid=444)
+--- Forum: Coding (https://hackforums.net/forumdisplay.php?fid=151)
+---- Forum: Coders Lounge (https://hackforums.net/forumdisplay.php?fid=5)
+---- Thread: [Help] Pytesseract OCR shipping labels (/showthread.php?tid=6264409)

Pytesseract OCR shipping labels - LatestGreatestPro - Feb 21, 2024

Hello all,
I recently joined this forum and upgraded and I love it here!

Anyways, my issue is i have shipping labels from UPS for my business and I want to use a script in python to extract the name of the recipient on the shipping label, the reference numbers, and the tracking number. Issue is when I run this script:

Code 
import cv2

import pytesseract

# Load image

img = cv2.imread("example_image.jpg")

# Convert image to grayscale

gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# Apply threshold to convert to binary image

threshold_img = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]

# Pass the image through pytesseract

text = pytesseract.image_to_string(threshold_img)

# Print the extracted text

print(text)

It’s inaccurate as shipping labels have different font sizes and the text can be quite close to each others (horizontally)

[Image: IMG-2928.png]

RE: Pytesseract OCR shipping labels - Hexicidal - Mar 1, 2024

You want a script that can scan the shipping label, and then extract the recognized string name correct?

RE: Pytesseract OCR shipping labels - LatestGreatestPro - Mar 3, 2024

I figured it out thanks ! Had to use simple rectangles with openCV and then resize it a throw that into pytesseract image to string function !