any experts out there offering there services?
want to improve on this simple script.
__________________________________
from pytesseract import image_to_string
import pytesseract
import cv2
import re
pytesseract.pytesseract.tesseract_cmd =
r'C:\Users\Bill-pc.Admin-PC\AppData\Local\Tesseract-OCR\tesseract.exe'
img = cv2.imread(r'D:\Bill-pc\Documents\Excel
Documents\PNG\2017-03-26_SecondPie.png', cv2.IMREAD_GRAYSCALE)
height, width = img.shape
roi = img[height - 41: height, 2: width]
roi = cv2.resize(roi, None, fx=1.006, fy=1.006)
_, th = cv2.threshold(roi, 253, 255, cv2.THRESH_BINARY)
text_detected = image_to_string(roi, config="--psm 10 --oem 3
tessedit_char_whitelist=0123456789", )
text_detected = re.sub('I', '1', text_detected)
text_detected = re.sub('i', '1', text_detected)
text_detected = re.sub('l', '1', text_detected)
text_detected = re.sub('L', '1', text_detected)
text_detected = re.sub('Z', '2', text_detected)
text_detected = re.sub('S', '5', text_detected)
text_detected = re.sub('s', '5', text_detected)
text_detected = re.sub('G', '6', text_detected)
numbers = re.findall("[0-9]+", text_detected)
print(text_detected)
cv2.imshow("th", roi)
print(numbers)
#print(text[5] + text[6] + text[7])
cv2.waitKey(0)
--
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
To view this discussion on the web visit
https://groups.google.com/d/msgid/tesseract-ocr/CAF5KrqBjrsGq0PBhSFmUV9%3D%3D3a_R47S471jwLsBSinAHOpVw9g%40mail.gmail.com.
