|
|
<!DOCTYPE html>
|
|
|
<!DOCTYPE html>
|
|
|
<html>
|
|
|
<head>
|
|
|
<meta charset="utf-8">
|
|
|
<title>Tasks of the Contingent Librarian</title>
|
|
|
<link rel="stylesheet" type="text/css" href="tasks.css">
|
|
|
<script src="tasks.js"></script>
|
|
|
</head>
|
|
|
<body>
|
|
|
|
|
|
<div class="cardback"><DOCUMENT_FRAGMENT><div class="mw-parser-output"><div class="thumb tright"><div class="thumbinner" style="width:152px;"><a class="image" href="File:Rereferencing_Open_work_OCR.jpeg.html"><img alt="" class="thumbimage" decoding="async" height="106" src="/mw-mediadesign/images/thumb/3/3c/Rereferencing_Open_work_OCR.jpeg/150px-Rereferencing_Open_work_OCR.jpeg" srcset="/mw-mediadesign/images/thumb/3/3c/Rereferencing_Open_work_OCR.jpeg/225px-Rereferencing_Open_work_OCR.jpeg 1.5x, /mw-mediadesign/images/thumb/3/3c/Rereferencing_Open_work_OCR.jpeg/300px-Rereferencing_Open_work_OCR.jpeg 2x" width="150"></a> <div class="thumbcaption"><div class="magnify"><a class="internal" href="File:Rereferencing_Open_work_OCR.jpeg.html" title="Enlarge"></a></div>A bootleg copy of The Open Work by Umberto Eco. OCR software has mistaken the page number (page 80) as the word “So”</div></div></div>
|
|
|
<p>Snippets:
|
|
|
</p>
|
|
|
<h2><span class="mw-headline" id="Pre-processing_for_OCR">Pre-processing for OCR</span><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/mw-mediadesign/index.php?title=User:Simon/self_directed_research/OCR_preprocessing&action=edit&section=T-1" title="Edit section: ">edit</a><span class="mw-editsection-bracket">]</span></span></h2>
|
|
|
<p>This script applies transformations to the image before running OCR, resulting in a clearer result:
|
|
|
</p><p><br>
|
|
|
</p>
|
|
|
<pre># 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)
|
|
|
</pre>
|
|
|
<!--
|
|
|
NewPP limit report
|
|
|
Cached time: 20200612082943
|
|
|
Cache expiry: 86400
|
|
|
Dynamic content: false
|
|
|
CPU time usage: 0.028 seconds
|
|
|
Real time usage: 0.041 seconds
|
|
|
Preprocessor visited node count: 7/1000000
|
|
|
Preprocessor generated node count: 26/1000000
|
|
|
Post‐expand include size: 187/2097152 bytes
|
|
|
Template argument size: 0/2097152 bytes
|
|
|
Highest expansion depth: 2/40
|
|
|
Expensive parser function count: 0/100
|
|
|
Unstrip recursion depth: 0/20
|
|
|
Unstrip post‐expand size: 1327/5000000 bytes
|
|
|
-->
|
|
|
<!--
|
|
|
Transclusion expansion time report (%,ms,calls,template)
|
|
|
100.00% 3.259 1 User:Simon/self_directed_research/OCR_preprocessing
|
|
|
100.00% 3.259 1 -total
|
|
|
-->
|
|
|
|
|
|
<!-- Saved in parser cache with key wdka_mw_mediadesign-mw_:pcache:idhash:31704-0!canonical and timestamp 20200612082943 and revision id 173944
|
|
|
-->
|
|
|
</div></DOCUMENT_FRAGMENT></div>
|
|
|
|
|
|
</body>
|
|
|
</html>
|