OpenCv pytesseract for OCR

2
votes

How to use opencv and pytesseract to extract text from image?

import cv2

import pytesseract from PIL import Image import numpy as np from matplotlib import pyplot as plt

img = Image.open('test.jpg').convert('L')
img.show()
img.save('test','png')
img = cv2.imread('test.png',0)
edges = cv2.Canny(img,100,200)
#contour = cv2.findContours(edges, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
#print pytesseract.image_to_string(Image.open(edges))
print pytesseract.image_to_string(edges)

But this is giving error-

Traceback (most recent call last): File "open.py", line 14, in print pytesseract.image_to_string(edges) File "/home/sroy8091/.local/lib/python2.7/site-packages/pytesseract/pytesseract.py", line 143, in image_to_string if len(image.split()) == 4: AttributeError: 'NoneType' object has no attribute 'split'

2
pythonopencv

2 Answers

7
votes

If you like to do some pre-processing using opencv (like you did some edge detection) and later on if you wantto extract text, you can use this command,

# All the imports and other stuffs goes here
img = cv2.imread('test.png',0)
edges = cv2.Canny(img,100,200)
img_new = Image.fromarray(edges)
text = pytesseract.image_to_string(img_new, lang='eng')
print (text)
0
votes

You cannot use directly Opencv objects with tesseract methods.

Try:

from PIL import Image
from pytesseract import *

image_file = 'test.png'
print(pytesseract.image_to_string(Image.open(image_file)))