User:Simon/self directed research/OCR preprocessing

From XPUB & Lens-Based wiki

Pre-processing for OCR:

   # import the necessary packages
  1. from PIL

import Image import pytesseract import argparse import cv2 import os

  1. construct the argument parse and parse the arguments

ap = argparse.ArgumentParser() ap.add_argument("-i", "--image", required=True, help="path to input image to be OCR'd") ap.add_argument("-p", "--preprocess", type=str, default="thresh", help="type of preprocessing to be done") args = vars(ap.parse_args())

  1. load the example image and convert it to grayscale

image = cv2.imread(args["image"]) gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

  1. check to see if we should apply thresholding to preprocess the
  2. image

if args["preprocess"] == "thresh": gray = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]

  1. make a check to see if median blurring should be done to remove
  2. noise

elif args["preprocess"] == "blur": gray = cv2.medianBlur(gray, 3)

  1. write the grayscale image to disk as a temporary file so we can
  2. apply OCR to it

filename = "{}.png".format(os.getpid()) cv2.imwrite(filename, gray)

  1. load the image as a PIL/Pillow image, apply OCR, and then delete
  2. the temporary file

text = pytesseract.image_to_string(Image.open(filename)) os.remove(filename) print(text)

  1. show the output images

cv2.imshow("Image", image) cv2.imshow("Output", gray) cv2.waitKey(0)