User:Simon/self directed research/OCR preprocessing: Difference between revisions

From XPUB & Lens-Based wiki
No edit summary
No edit summary
Line 2: Line 2:


     # import the necessary packages
     # import the necessary packages
#from PIL  
    #from PIL  
import Image
    import Image
import pytesseract
    import pytesseract
import argparse
    import argparse
import cv2
    import cv2
import os
    import os


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


# load the example image and convert it to grayscale
    # load the example image and convert it to grayscale
image = cv2.imread(args["image"])
    image = cv2.imread(args["image"])
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)


# check to see if we should apply thresholding to preprocess the
    # check to see if we should apply thresholding to preprocess the
# image
    # image
if args["preprocess"] == "thresh":
    if args["preprocess"] == "thresh":
gray = cv2.threshold(gray, 0, 255,
gray = cv2.threshold(gray, 0, 255,
cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
    cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]


# make a check to see if median blurring should be done to remove
    # make a check to see if median blurring should be done to remove
# noise
    # noise
elif args["preprocess"] == "blur":
    elif args["preprocess"] == "blur":
gray = cv2.medianBlur(gray, 3)
gray = cv2.medianBlur(gray, 3)


# write the grayscale image to disk as a temporary file so we can
    # write the grayscale image to disk as a temporary file so we can
# apply OCR to it
    # apply OCR to it
filename = "{}.png".format(os.getpid())
    filename = "{}.png".format(os.getpid())
cv2.imwrite(filename, gray)
    cv2.imwrite(filename, gray)


# load the image as a PIL/Pillow image, apply OCR, and then delete
    # load the image as a PIL/Pillow image, apply OCR, and then delete
# the temporary file
    # the temporary file
text = pytesseract.image_to_string(Image.open(filename))
    text = pytesseract.image_to_string(Image.open(filename))
os.remove(filename)
    os.remove(filename)
print(text)
    print(text)


# show the output images
    # show the output images
cv2.imshow("Image", image)
    cv2.imshow("Image", image)
cv2.imshow("Output", gray)
    cv2.imshow("Output", gray)
cv2.waitKey(0)</code>
    cv2.waitKey(0)</code>

Revision as of 16:21, 5 September 2019

Pre-processing for OCR:

   # import the necessary packages
   #from PIL 
   import Image
   import pytesseract
   import argparse
   import cv2
   import os
   # 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())
   # load the example image and convert it to grayscale
   image = cv2.imread(args["image"])
   gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
   # check to see if we should apply thresholding to preprocess the
   # image
   if args["preprocess"] == "thresh":

gray = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]

   # make a check to see if median blurring should be done to remove
   # noise
   elif args["preprocess"] == "blur":

gray = cv2.medianBlur(gray, 3)

   # write the grayscale image to disk as a temporary file so we can
   # apply OCR to it
   filename = "{}.png".format(os.getpid())
   cv2.imwrite(filename, gray)
   # load the image as a PIL/Pillow image, apply OCR, and then delete
   # the temporary file
   text = pytesseract.image_to_string(Image.open(filename))
   os.remove(filename)
   print(text)
   # show the output images
   cv2.imshow("Image", image)
   cv2.imshow("Output", gray)
   cv2.waitKey(0)