-
Notifications
You must be signed in to change notification settings - Fork 50
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Added basic script to generate simple HTML from entire image processi…
…ng chain. Needs lots of work, but a good start.
- Loading branch information
Showing
3 changed files
with
136 additions
and
61 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,112 @@ | ||
| #!/usr/bin/python | ||
| # vim: set ts=2 expandtab: | ||
| """ | ||
| Module: ocr | ||
| Desc: | ||
| Author: John O'Neil | ||
| Email: [email protected] | ||
| DATE: Saturday, August 25th 2013 | ||
| Front to back end Manga text detection. | ||
| Input is image file of raw manga image | ||
| Output is HTML page annotating image with detected text. | ||
| """ | ||
| #import clean_page as clean | ||
| import connected_components as cc | ||
| import run_length_smoothing as rls | ||
| import clean_page as clean | ||
| import ocr | ||
|
|
||
| import numpy as np | ||
| import cv2 | ||
| import sys | ||
| import argparse | ||
| import os | ||
| import scipy.ndimage | ||
| #from pylab import zeros,amax,median | ||
|
|
||
|
|
||
| if __name__ == '__main__': | ||
|
|
||
| parser = argparse.ArgumentParser(description='Generate HTML annotation for raw manga scan with detected OCR\'d text.') | ||
| parser.add_argument('infile', help='Input (color) raw Manga scan image to annoate.') | ||
| parser.add_argument('-o','--output', dest='outfile', help='Output html file.') | ||
| #parser.add_argument('-m','--mask', dest='mask', default=None, help='Output (binary) mask for non-graphical regions.') | ||
| #parser.add_argument('-b','--binary', dest='binary', default=None, help='Binarized version of input file.') | ||
| parser.add_argument('--verbose', help='Verbose operation. Print status messages during processing', action="store_true") | ||
| parser.add_argument('--display', help='Display output using OPENCV api and block program exit.', action="store_true") | ||
|
|
||
| args = parser.parse_args() | ||
| infile = args.infile | ||
| outfile = infile + '.html' | ||
| if args.outfile is not None: | ||
| outfile = args.outfile | ||
|
|
||
| img = cv2.imread(sys.argv[1]) | ||
| (h,w)=img.shape[:2] | ||
|
|
||
| gray = clean.grayscale(img) | ||
|
|
||
| gaussian_filtered = scipy.ndimage.gaussian_filter(gray, sigma=1.5) | ||
| gaussian_binary = clean.binarize(gaussian_filtered) | ||
| average_size = cc.average_size(gaussian_binary) | ||
|
|
||
| (binary,mask,cleaned) = clean.clean_image_file(infile) | ||
|
|
||
| #use multiple of average size as vertical threshold for run length smoothing | ||
| vertical_smoothing_threshold = 0.75*average_size | ||
| horizontal_smoothing_threshold = 0.75*average_size | ||
|
|
||
| inv_cleaned = cv2.bitwise_not(cleaned) | ||
| inv_binary = cv2.bitwise_not(binary) | ||
| run_length_smoothed_or = rls.RLSO(inv_cleaned, horizontal_smoothing_threshold, vertical_smoothing_threshold) | ||
|
|
||
| components = cc.get_connected_components(run_length_smoothed_or) | ||
|
|
||
| #perhaps do more strict filtering of connected components because sections of characters | ||
| #will not be dripped from run length smoothed areas? Yes. Results quite good. | ||
| filtered = cc.filter_by_size(img,components,average_size*100,average_size*1) | ||
|
|
||
| #Build html page with image | ||
| from django.template import Template, Context | ||
| from django.conf import settings | ||
| from django.template.loader import render_to_string | ||
| settings.configure() | ||
| blurbs = ocr.ocr_on_bounding_boxes(inv_binary, filtered) | ||
| template = u''' | ||
| <html> | ||
| <head> | ||
| <title>{{ image }}</title> | ||
| </head> | ||
| <body> | ||
| <h1>{{ image }}.</h1> | ||
| <img src="{{ image }}" alt="{{ image }}"/> | ||
| {% for blurb in blurbs %} | ||
| {{ blurb.confidence }} - {{ blurb.text }}<br> | ||
| <hl> | ||
| {% endfor %} | ||
| </body> | ||
| </html> | ||
| ''' | ||
|
|
||
| t = Template(template) | ||
| c = Context({"image": infile, | ||
| "blurbs":blurbs}) | ||
| #print t.render(c) | ||
| #for blurb in blurbs: | ||
| # print str(blurb.confidence)+'% :'+ blurb.text | ||
| #open(outfile, "w").write(render_to_string(template, c)) | ||
| open(outfile, "w").write(t.render(c).encode("utf-8")) | ||
|
|
||
|
|
||
| if args.display: | ||
| cv2.imshow('img',img) | ||
| #cv2.imwrite('segmented.png',img) | ||
| cv2.imshow('run_length_smoothed_or',run_length_smoothed_or) | ||
| #cv2.imwrite('run_length_smoothed.png',run_length_smoothed_or) | ||
| #cv2.imwrite('cleaned.png',cleaned) | ||
|
|
||
| if cv2.waitKey(0) == 27: | ||
| cv2.destroyAllWindows() | ||
| cv2.destroyAllWindows() |
File renamed without changes.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters