Unable to get the correct OCR text Python-CodePudding

I am trying to read the text from a .png file, but unable to get the proper output.

Here is the code I have tried:

from PIL import Image
from pytesseract import pytesseract

path_to_tesseract = r"Path_to Tesseract-OCR.exe"

image_path = r"Path to png file"

img = Image.open(image_path)

pytesseract.tesseract_cmd = path_to_tesseract

text = pytesseract.image_to_string(img)

print(text)

The output I'm getting is something like this: m _ an I: umonfé ‘

Input .png file:

The expected output is LG485169046

CodePudding user response：

I would like to suggest you using

Output will be:

LABGROWN IGI LG485169046

If you only want the last part, you could do:

>>> print(text.split(" ")[3])
LG485169046

Code:

import cv2
import pytesseract


# Load the image
img = cv2.imread("KfzeJ.png")

# Resize the image
img = cv2.resize(img, None, fx=2, fy=2)

# Convert to the hsv color-space
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)

# Get binary-mask
msk = cv2.inRange(hsv, array([0, 0, 0]), array([179, 255, 80]))
krn = cv2.getStructuringElement(cv2.MORPH_RECT, (5, 3))
dlt = cv2.dilate(msk, krn, iterations=1)
thr = 255 - cv2.bitwise_and(dlt, msk)

# OCR
txt = pytesseract.image_to_string(thr)
print(txt.split(" ")[3])

P.S. Pytesseract version: 0.3.8

CodePudding user response：

Step1- try to add the "Path_to Tesseract-OCR.exe" to your environment variable.

Step2- if step1 not worked try to use passporteye package.