I tried following code . I want to extract text along with *** symbol . I
tired following code
import cv2
import pytesseract
import numpy as np
def image_resize(image, width = None, height = None, inter =
cv2.INTER_AREA):
# initialize the dimensions of the image to be resized and
# grab the image size
dim = None
(h, w) = image.shape[:2]
# if both the width and height are None, then return the
# original image
if width is None and height is None:
return image
# check to see if the width is None
if width is None:
# calculate the ratio of the height and construct the
# dimensions
r = height / float(h)
dim = (int(w * r), height)
# otherwise, the height is None
else:
# calculate the ratio of the width and construct the
# dimensions
r = width / float(w)
dim = (width, int(h * r))
# resize the image
resized = cv2.resize(image, dim, interpolation = cv2.INTER_LINEAR)
# return the resized image
return resized
img = cv2.imread('test.jpg' ,0)
img = image_resize(img, height = 4000)
print(pytesseract.image_to_string(img, config=' -c textord_heavy_nr=0
textord_noise_area_ratio =100 textord_max_noise_size = 154 --psm 11 ' ))
--
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 post to this group, send email to [email protected].
Visit this group at https://groups.google.com/group/tesseract-ocr.
To view this discussion on the web visit
https://groups.google.com/d/msgid/tesseract-ocr/89d10b5b-118c-4306-baff-5104788e30cc%40googlegroups.com.
For more options, visit https://groups.google.com/d/optout.
