def segmenter(text_direction, script_detect, allowed_scripts, scale,
maxcolseps, black_colseps, remove_hlines, pad, base_image, input,
output) -> None:
import json
from kraken import pageseg
try:
im = Image.open(input)
except IOError as e:
raise click.BadParameter(str(e))
message('Segmenting\t', nl=False)
try:
res = pageseg.segment(im,
text_direction,
scale,
maxcolseps,
black_colseps,
no_hlines=remove_hlines,
pad=pad)
if script_detect:
res = pageseg.detect_scripts(im,
res,
valid_scripts=allowed_scripts)
except Exception:
message('\u2717', fg='red')
raise
with open_file(output, 'w') as fp:
fp = cast(IO[Any], fp)
json.dump(res, fp)
message('\u2713', fg='green')
def segmenter(text_direction, script_detect, allowed_scripts, scale,
maxcolseps, black_colseps, remove_hlines, pad, mask, base_image, input,
output) -> None:
import json
from kraken import pageseg
try:
im = Image.open(input)
except IOError as e:
raise click.BadParameter(str(e))
if mask:
try:
mask = Image.open(mask)
except IOError as e:
raise click.BadParameter(str(e))
message('Segmenting\t', nl=False)
try:
res = pageseg.segment(im, text_direction, scale, maxcolseps, black_colseps, no_hlines=remove_hlines, pad=pad, mask=mask)
if script_detect:
res = pageseg.detect_scripts(im, res, valid_scripts=allowed_scripts)
except Exception:
message('\u2717', fg='red')
raise
with open_file(output, 'w') as fp:
fp = cast(IO[Any], fp)
json.dump(res, fp)
message('\u2713', fg='green')
def segmenter(text_direction, script_detect, scale, maxcolseps, black_colseps, base_image, input, output):
try:
im = Image.open(input)
except IOError as e:
raise click.BadParameter(str(e))
click.echo('Segmenting\t', nl=False)
try:
res = pageseg.segment(im, text_direction, scale, maxcolseps, black_colseps)
if script_detect:
res = pageseg.detect_scripts(im, res)
except:
click.secho(u'\u2717', fg='red')
raise
with open_file(output, 'w') as fp:
json.dump(res, fp)
click.secho(u'\u2713', fg='green')
def process(self):
"""
Segment with kraken
"""
log = getLogger('processor.KrakenSegment')
for (n, input_file) in enumerate(self.input_files):
log.info("INPUT FILE %i / %s", n, input_file)
downloaded_file = self.workspace.download_file(input_file)
log.info("downloaded_file %s", downloaded_file)
pcgts = page_from_file(downloaded_file)
# TODO binarized variant from get_AlternativeImage()
image_url = pcgts.get_Page().imageFilename
log.info("pcgts %s", pcgts)
im = self.workspace.resolve_image_as_pil(image_url)
log.info('Segmenting')
log.info('Params %s', self.parameter)
res = segment(im, self.parameter['text_direction'],
self.parameter['scale'],
self.parameter['maxcolseps'],
self.parameter['black_colseps'])
if self.parameter['script_detect']:
res = detect_scripts(im, res)
dummyRegion = TextRegionType()
pcgts.get_Page().add_TextRegion(dummyRegion)
# print(res)
for lineno, box in enumerate(res['boxes']):
textline = TextLineType(
id=concat_padded("line", lineno),
Coords=CoordsType(points=points_from_x0y0x1y1(box)))
dummyRegion.add_TextLine(textline)
ID = concat_padded(self.output_file_grp, n)
self.workspace.add_file(self.output_file_grp,
pageId=input_file.pageId,
ID=ID,
mimetype=MIMETYPE_PAGE,
local_filename="%s/%s.xml" %
(self.output_file_grp, ID),
content=to_xml(pcgts).encode('utf-8'))