OCR With Opencv Python

In this instructables im going to tell you how to perform Optical Character Recognition using Google's Tesseract engine.

for opencv /python installation see this link below

https://www.instructables.com/id/Opencv-and-Python...

for tesseract click below

https://github.com/tesseract-ocr/tesseract

Step 1: Python Code

The combination of python and opencv with tesseract Engine

from PIL import Image
import pytesseract
import numpy as np
import argparse
import cv2, os
# parse the argument
parser = argparse.ArgumentParser()
parser.add_argument("-i", "--image", required = True)
parser.add_argument("-p", "--preprocess", type = str, default = "thresh")
args = vars(parser.parse_args())
# load the example image and convert it to grayscale
image = cv2.imread(args["image"])
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
 
# check preprocess to apply thresholding on the image
if args["preprocess"] == "thresh":
	gray = cv2.threshold(gray, 0, 255,
		cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
 
elif args["preprocess"] == "blur":
	gray = cv2.medianBlur(gray, 3)
 
# write the grayscale image to disk as a temporary file
filename = "{}.png".format(os.getpid())
cv2.imwrite(filename, gray)
# load the image as a PIL/Pillow image
# apply OCR
# delete temp image
text = pytesseract.image_to_string(Image.open(filename))
os.remove(filename)
#TO-DO : Additional processing such as spellchecking for OCR errors or NLP 
print(text)
 
# show the output images
cv2.imshow("Image", image)
cv2.imshow("Output", gray)
cv2.waitKey(0)
cv2.destroyAllWindows()

Step 2: How to Run the Python Code

Open terminal

Run command in this sequence :

$ python ocr.py -image image.jpg

(Applying Gaussian Blur/Thresholding)

$ python ocr.py -image image.jpg -preprocess blur

Now you would see the image and text will be printed in the terminal.