def main():
parser = arg.parser
parser = argparse.ArgumentParser(description='Basic OCR on raw manga scan.')
parser.add_argument('infile', help='Input (color) raw Manga scan image to clean.')
parser.add_argument('-o','--output', dest='outfile', help='Output (color) cleaned raw manga scan image.')
parser.add_argument('-v','--verbose', help='Verbose operation. Print status messages during processing', action="store_true")
#parser.add_argument('-d','--debug', help='Overlay input image into output.', action="store_true")
parser.add_argument('--sigma', help='Std Dev of gaussian preprocesing filter.',type=float,default=None)
parser.add_argument('--binary_threshold', help='Binarization threshold value from 0 to 255.',type=int,default=defaults.BINARY_THRESHOLD)
parser.add_argument('--furigana', help='Attempt to suppress furigana characters to improve OCR.', action="store_true")
parser.add_argument('--segment_threshold', help='Threshold for nonzero pixels to separete vert/horiz text lines.',type=int,default=defaults.SEGMENTATION_THRESHOLD)
arg.value = parser.parse_args()
infile = arg.string_value('infile')
outfile = arg.string_value('outfile', default_value=infile + '.html')
if not os.path.isfile(infile):
print ('Please provide a regular existing input file. Use -h option for help.')
sys.exit(-1)
if arg.boolean_value('verbose'):
print ('\tProcessing file ' + infile)
print ('\tGenerating output ' + outfile)
img = cv2.imread(infile)
gray = clean.grayscale(img)
binary = clean.binarize(gray)
segmented = segmentation.segment_image_file(infile)
components = cc.get_connected_components(segmented)
#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)
blurbs = ocr_on_bounding_boxes(binary, components)
for blurb in blurbs:
print (str(blurb.x)+','+str(blurb.y)+' '+str(blurb.w)+'x'+str(blurb.h)+' '+ str(blurb.confidence)+'% :'+ blurb.text)
def main():
parser = arg.parser
parser = argparse.ArgumentParser(description='Basic OCR on raw manga scan.')
parser.add_argument('infile', help='Input (color) raw Manga scan image to clean.')
parser.add_argument('-o','--output', dest='outfile', help='Output (color) cleaned raw manga scan image.')
parser.add_argument('-v','--verbose', help='Verbose operation. Print status messages during processing', action="store_true")
#parser.add_argument('-d','--debug', help='Overlay input image into output.', action="store_true")
parser.add_argument('--sigma', help='Std Dev of gaussian preprocesing filter.',type=float,default=None)
parser.add_argument('--binary_threshold', help='Binarization threshold value from 0 to 255.',type=int,default=defaults.BINARY_THRESHOLD)
parser.add_argument('--furigana', help='Attempt to suppress furigana characters to improve OCR.', action="store_true")
parser.add_argument('--segment_threshold', help='Threshold for nonzero pixels to separete vert/horiz text lines.',type=int,default=defaults.SEGMENTATION_THRESHOLD)
arg.value = parser.parse_args()
infile = arg.string_value('infile')
outfile = arg.string_value('outfile', default_value=infile + '.html')
if not os.path.isfile(infile):
print 'Please provide a regular existing input file. Use -h option for help.'
sys.exit(-1)
if arg.boolean_value('verbose'):
print '\tProcessing file ' + infile
print '\tGenerating output ' + outfile
img = cv2.imread(infile)
gray = clean.grayscale(img)
binary = clean.binarize(gray)
segmented = segmentation.segment_image_file(infile)
components = cc.get_connected_components(segmented)
#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)
blurbs = ocr_on_bounding_boxes(binary, components)
for blurb in blurbs:
print str(blurb.x)+','+str(blurb.y)+' '+str(blurb.w)+'x'+str(blurb.h)+' '+ str(blurb.confidence)+'% :'+ blurb.text