def cli(format_type, model, repolygonize, files):
"""
A small script extracting rectified line polygons as defined in either ALTO or
PageXML files or run a model to do the same.
"""
if len(files) == 0:
ctx = click.get_current_context()
click.echo(ctx.get_help())
ctx.exit()
from PIL import Image
from os.path import splitext
from kraken import blla
from kraken.lib import dataset, segmentation, vgsl, xml
if model is None:
for doc in files:
click.echo(f'Processing {doc} ', nl=False)
data = xml.preparse_xml_data([doc], format_type, repolygonize=repolygonize)
if len(data) > 0:
bounds = {'type': 'baselines', 'lines': [{'boundary': t['boundary'], 'baseline': t['baseline'], 'text': t['text']} for t in data]}
for idx, (im, box) in enumerate(segmentation.extract_polygons(Image.open(data[0]['image']), bounds)):
click.echo('.', nl=False)
im.save('{}.{}.jpg'.format(splitext(data[0]['image'])[0], idx))
with open('{}.{}.gt.txt'.format(splitext(data[0]['image'])[0], idx), 'w') as fp:
fp.write(box['text'])
else:
net = vgsl.TorchVGSLModel.load_model(model)
for doc in files:
click.echo(f'Processing {doc} ', nl=False)
full_im = Image.open(doc)
bounds = blla.segment(full_im, model=net)
for idx, (im, box) in enumerate(segmentation.extract_polygons(full_im, bounds)):
click.echo('.', nl=False)
im.save('{}.{}.jpg'.format(splitext(doc)[0], idx))
def segmenter(legacy, model, text_direction, scale, maxcolseps, black_colseps,
remove_hlines, pad, mask, device, input, output) -> None:
import json
from kraken import pageseg
from kraken import blla
ctx = click.get_current_context()
if ctx.meta['first_process']:
if ctx.meta['input_format_type'] != 'image':
input = get_input_parser(
ctx.meta['input_format_type'])(input)['image']
ctx.meta['first_process'] = False
if 'base_image' not in ctx.meta:
ctx.meta['base_image'] = input
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:
if legacy:
res = pageseg.segment(im,
text_direction,
scale,
maxcolseps,
black_colseps,
no_hlines=remove_hlines,
pad=pad,
mask=mask)
else:
res = blla.segment(im,
text_direction,
mask=mask,
model=model,
device=device)
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(legacy, model, text_direction, scale, maxcolseps, black_colseps,
remove_hlines, pad, mask, device, input, output) -> None:
import json
from kraken import pageseg
from kraken import blla
ctx = click.get_current_context()
if ctx.meta['first_process']:
if ctx.meta['input_format_type'] != 'image':
input = get_input_parser(
ctx.meta['input_format_type'])(input)['image']
ctx.meta['first_process'] = False
if 'base_image' not in ctx.meta:
ctx.meta['base_image'] = input
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:
if legacy:
res = pageseg.segment(im,
text_direction,
scale,
maxcolseps,
black_colseps,
no_hlines=remove_hlines,
pad=pad,
mask=mask)
else:
res = blla.segment(im,
text_direction,
mask=mask,
model=model,
device=device)
except Exception:
message('\u2717', fg='red')
raise
if ctx.meta['last_process'] and ctx.meta['output_mode'] != 'native':
with open_file(output, 'w', encoding='utf-8') as fp:
fp = cast(IO[Any], fp)
logger.info('Serializing as {} into {}'.format(
ctx.meta['output_mode'], output))
from kraken import serialization
from kraken.rpred import ocr_record
if 'type' in res and res['type'] == 'baselines':
records = [ocr_record('', '', '', bl) for bl in res['lines']]
else:
records = []
for line in res['boxes']:
xmin, xmax = min(line[::2]), max(line[::2])
ymin, ymax = min(line[1::2]), max(line[1::2])
records.append(
ocr_record('', [], [], [[xmin, ymin], [xmin, ymax],
[xmax, ymax], [xmax, ymin]]))
fp.write(
serialization.serialize(
records,
image_name=ctx.meta['base_image'],
image_size=im.size,
regions=res['regions'] if 'regions' in res else None,
template=ctx.meta['output_mode']))
else:
with open_file(output, 'w') as fp:
fp = cast(IO[Any], fp)
json.dump(res, fp)
message('\u2713', fg='green')
def segmenter(legacy, model, text_direction, scale, maxcolseps, black_colseps,
remove_hlines, pad, mask, device, input, output) -> None:
import json
from kraken import pageseg
from kraken import blla
ctx = click.get_current_context()
if ctx.meta['first_process']:
if ctx.meta['input_format_type'] != 'image':
input = get_input_parser(
ctx.meta['input_format_type'])(input)['image']
ctx.meta['first_process'] = False
if 'base_image' not in ctx.meta:
ctx.meta['base_image'] = input
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:
if legacy:
res = pageseg.segment(im,
text_direction,
scale,
maxcolseps,
black_colseps,
no_hlines=remove_hlines,
pad=pad,
mask=mask)
else:
res = blla.segment(im,
text_direction,
mask=mask,
model=model,
device=device)
except Exception:
if ctx.meta['raise_failed']:
raise
message('\u2717', fg='red')
ctx.exit(1)
if ctx.meta['last_process'] and ctx.meta['output_mode'] != 'native':
with click.open_file(output, 'w', encoding='utf-8') as fp:
fp = cast(IO[Any], fp)
logger.info('Serializing as {} into {}'.format(
ctx.meta['output_mode'], output))
from kraken import serialization
from kraken.rpred import ocr_record
fp.write(
serialization.serialize_segmentation(
res,
image_name=ctx.meta['base_image'],
image_size=im.size,
template=ctx.meta['output_mode']))
else:
with click.open_file(output, 'w') as fp:
fp = cast(IO[Any], fp)
json.dump(res, fp)
message('\u2713', fg='green')
def cli(format_type, model, repolygonize, files):
"""
A script producing overlays of lines and regions from either ALTO or
PageXML files or run a model to do the same.
"""
if len(files) == 0:
ctx = click.get_current_context()
click.echo(ctx.get_help())
ctx.exit()
from PIL import Image, ImageDraw
from kraken.lib import vgsl, xml
from kraken import blla
if model is None:
if format_type == 'xml':
fn = xml.parse_xml
elif format_type == 'alto':
fn = xml.parse_palto
else:
fn = xml.parse_page
for doc in files:
click.echo(f'Processing {doc} ', nl=False)
data = fn(doc)
# reorder lines by type
lines = defaultdict(list)
for line in data['lines']:
lines[line['script']].append(line)
im = Image.open(data['image']).convert('RGBA')
for t, ls in lines.items():
tmp = Image.new('RGBA', im.size, (0, 0, 0, 0))
draw = ImageDraw.Draw(tmp)
for idx, line in enumerate(ls):
c = next(cmap)
if line['boundary']:
draw.polygon([tuple(x) for x in line['boundary']],
fill=c,
outline=c[:3])
if line['baseline']:
draw.line([tuple(x) for x in line['baseline']],
fill=bmap,
width=2,
joint='curve')
draw.text(line['baseline'][0],
str(idx),
fill=(0, 0, 0, 255))
base_image = Image.alpha_composite(im, tmp)
base_image.save(f'high_{os.path.basename(doc)}_lines_{t}.png')
for t, regs in data['regions'].items():
tmp = Image.new('RGBA', im.size, (0, 0, 0, 0))
draw = ImageDraw.Draw(tmp)
for reg in regs:
c = next(cmap)
draw.polygon(reg, fill=c, outline=c[:3])
base_image = Image.alpha_composite(im, tmp)
base_image.save(
f'high_{os.path.basename(doc)}_regions_{t}.png')
click.secho('\u2713', fg='green')
else:
net = vgsl.TorchVGSLModel.load_model(model)
for doc in files:
click.echo(f'Processing {doc} ', nl=False)
im = Image.open(doc)
res = blla.segment(im, model=net)
# reorder lines by type
lines = defaultdict(list)
for line in res['lines']:
lines[line['script']].append(line)
im = im.convert('RGBA')
for t, ls in lines.items():
tmp = Image.new('RGBA', im.size, (0, 0, 0, 0))
draw = ImageDraw.Draw(tmp)
for idx, line in enumerate(ls):
c = next(cmap)
draw.polygon([tuple(x) for x in line['boundary']],
fill=c,
outline=c[:3])
draw.line([tuple(x) for x in line['baseline']],
fill=bmap,
width=2,
joint='curve')
draw.text(line['baseline'][0],
str(idx),
fill=(0, 0, 0, 255))
base_image = Image.alpha_composite(im, tmp)
base_image.save(f'high_{os.path.basename(doc)}_lines_{t}.png')
for t, regs in res['regions'].items():
tmp = Image.new('RGBA', im.size, (0, 0, 0, 0))
draw = ImageDraw.Draw(tmp)
for reg in regs:
c = next(cmap)
draw.polygon([tuple(x) for x in reg],
fill=c,
outline=c[:3])
base_image = Image.alpha_composite(im, tmp)
base_image.save(
f'high_{os.path.basename(doc)}_regions_{t}.png')
click.secho('\u2713', fg='green')