def pagexmllineseg(xmlfile, text_direction = 'horizontal-lr', outputfile=None):
"""
Opens file 'xmlfile', converts to newest pagexml version 2017,
segments the text regions and writes xml to file.
Output is written to input file if outfile is 'None'.
"""
if not outputfile:
outputfile = xmlfile
root = etree.parse(xmlfile).getroot()
ns = {"ns":root.nsmap[None]}
#convert point notation from older pagexml versions
for c in root.xpath("//ns:Coords[not(@points)]", namespaces=ns):
cc = []
for point in c.xpath("./ns:Point", namespaces=ns):
#coordstrings = [x.split(",") for x in c.attrib["points"].split()]
cx = point.attrib["x"]
cy = point.attrib["y"]
c.remove(point)
cc.append(cx+","+cy)
c.attrib["points"] = " ".join(cc)
coordmap = {}
for r in root.xpath('//ns:TextRegion', namespaces=ns):
rid = r.attrib["id"]
coordmap[rid] = {"type":r.attrib["type"]}
coordmap[rid]["coords"] = []
for c in r.xpath("./ns:Coords", namespaces=ns) + r.xpath("./Coords"):
coordstrings = [x.split(",") for x in c.attrib["points"].split()]
coordmap[rid]["coords"] += [[int(x[0]), int(x[1])] for x in coordstrings ]
filename = root.xpath('//ns:Page', namespaces=ns)[0].attrib["imageFilename"]
im = Image.open(filename)
for n, c in enumerate(sorted(coordmap)):
coords = coordmap[c]['coords']
cropped = cutout(im, coords)
offset = (min([x[0] for x in coords]), min([x[1] for x in coords]))
if cropped != None:
if not binarization.is_bitonal(cropped):
cropped = binarization.nlbin(cropped)
lines = segment(cropped, text_direction=text_direction, maxcolseps=0)['lines']
else:
lines = []
for n, l in enumerate(lines):
coords = ((x[1]+offset[0], x[0]+offset[1]) for x in l.polygon)
coordstrg = " ".join(str(x[0])+","+str(x[1]) for x in coords)
textregion = root.xpath('//ns:TextRegion[@id="'+c+'"]', namespaces=ns)[0]
linexml = etree.SubElement(textregion, "TextLine",
attrib={"id":c+"_l{:03d}".format(n + 1)})
coordsxml = etree.SubElement(linexml, "Coords",
attrib={"points":coordstrg})
xmlstring = etree.tounicode(root.getroottree()).replace(
"http://schema.primaresearch.org/PAGE/gts/pagecontent/2010-03-19",
"http://schema.primaresearch.org/PAGE/gts/pagecontent/2017-07-15"
)
with open(outputfile, "w") as f:
f.write(xmlstring)
def transcription(ctx, text_direction, scale, maxcolseps, black_colseps, font,
font_style, prefill, output, images):
st_time = time.time()
ti = transcribe.TranscriptionInterface(font, font_style)
if prefill:
if ctx.meta['verbose'] > 0:
click.echo(u'[{:2.4f}] Loading model {}'.format(time.time() - st_time, prefill))
else:
spin('Loading RNN')
prefill = models.load_any(prefill.encode('utf-8'))
if not ctx.meta['verbose']:
click.secho(u'\b\u2713', fg='green', nl=False)
click.echo('\033[?25h\n', nl=False)
for fp in images:
if ctx.meta['verbose'] > 0:
click.echo(u'[{:2.4f}] Reading {}'.format(time.time() - st_time, fp.name))
else:
spin('Reading images')
im = Image.open(fp)
if not binarization.is_bitonal(im):
if ctx.meta['verbose'] > 0:
click.echo(u'[{:2.4f}] Binarizing page'.format(time.time() - st_time))
im = binarization.nlbin(im)
if ctx.meta['verbose'] > 0:
click.echo(u'[{:2.4f}] Segmenting page'.format(time.time() - st_time))
res = pageseg.segment(im, text_direction, scale, maxcolseps, black_colseps)
if prefill:
it = rpred.rpred(prefill, im, res)
preds = []
for pred in it:
if ctx.meta['verbose'] > 0:
click.echo(u'[{:2.4f}] {}'.format(time.time() - st_time, pred.prediction))
else:
spin('Recognizing')
preds.append(pred)
if ctx.meta['verbose'] > 0:
click.echo(u'Execution time: {}s'.format(time.time() - st_time))
else:
click.secho(u'\b\u2713', fg='green', nl=False)
click.echo('\033[?25h\n', nl=False)
ti.add_page(im, res, records=preds)
else:
ti.add_page(im, res)
fp.close()
if not ctx.meta['verbose']:
click.secho(u'\b\u2713', fg='green', nl=False)
click.echo('\033[?25h\n', nl=False)
if ctx.meta['verbose'] > 0:
click.echo(u'[{:2.4f}] Writing transcription to {}'.format(time.time() - st_time, output.name))
else:
spin('Writing output')
ti.write(output)
if not ctx.meta['verbose']:
click.secho(u'\b\u2713', fg='green', nl=False)
click.echo('\033[?25h\n', nl=False)
def transcription(ctx, font, font_style, prefill, output, images):
st_time = time.time()
ti = transcrib.TranscriptionInterface(font, font_style)
if prefill:
if ctx.meta['verbose'] > 0:
click.echo(u'[{:2.4f}] Loading model {}'.format(time.time() - st_time, prefill))
else:
spin('Loading RNN')
prefill = models.load_any(prefill)
if not ctx.meta['verbose']:
click.secho(u'\b\u2713', fg='green', nl=False)
click.echo('\033[?25h\n', nl=False)
for fp in images:
if ctx.meta['verbose'] > 0:
click.echo(u'[{:2.4f}] Reading {}'.format(time.time() - st_time, fp.name))
else:
spin('Reading images')
im = Image.open(fp)
if not binarization.is_bitonal(im):
if ctx.meta['verbose'] > 0:
click.echo(u'[{:2.4f}] Binarizing page'.format(time.time() - st_time))
im = binarization.nlbin(im)
if ctx.meta['verbose'] > 0:
click.echo(u'[{:2.4f}] Segmenting page'.format(time.time() - st_time))
res = pageseg.segment(im)
if prefill:
it = rpred.rpred(prefill, im, res)
preds = []
for pred in it:
if ctx.meta['verbose'] > 0:
click.echo(u'[{:2.4f}] {}'.format(time.time() - st_time, pred.prediction))
else:
spin('Recognizing')
preds.append(pred)
if ctx.meta['verbose'] > 0:
click.echo(u'Execution time: {}s'.format(time.time() - st_time))
else:
click.secho(u'\b\u2713', fg='green', nl=False)
click.echo('\033[?25h\n', nl=False)
ti.add_page(im, records=preds)
else:
ti.add_page(im, res)
if not ctx.meta['verbose']:
click.secho(u'\b\u2713', fg='green', nl=False)
click.echo('\033[?25h\n', nl=False)
if ctx.meta['verbose'] > 0:
click.echo(u'[{:2.4f}] Writing transcription to {}'.format(time.time() - st_time, output.name))
else:
spin('Writing output')
ti.write(output)
if not ctx.meta['verbose']:
click.secho(u'\b\u2713', fg='green', nl=False)
click.echo('\033[?25h\n', nl=False)
def segment(im, scale=None, black_colseps=False):
"""
Segments a page into text lines.
Segments a page into text lines and returns the absolute coordinates of
each line in reading order.
Args:
im (PIL.Image): A bi-level page of mode '1' or 'L'
scale (float): Scale of the image
black_colseps (bool): Whether column separators are assumed to be
vertical black lines or not
Returns:
[(x1, y1, x2, y2),...]: A list of tuples containing the bounding boxes
of the segmented lines in reading order.
Raises:
KrakenInputException if the input image is not binarized
"""
if im.mode != '1' and not is_bitonal(im):
raise KrakenInputException('Image is not bi-level')
# honestly I've got no idea what's going on here. In theory a simple
# np.array(im, 'i') should suffice here but for some reason the
# tostring/fromstring magic in pil2array alters the array in a way that is
# needed for the algorithm to work correctly.
a = pil2array(im)
binary = np.array(a > 0.5 * (np.amin(a) + np.amax(a)), 'i')
binary = 1 - binary
if not scale:
scale = estimate_scale(binary)
binary = remove_hlines(binary, scale)
if black_colseps:
colseps, binary = compute_black_colseps(binary, scale)
else:
colseps = compute_white_colseps(binary, scale)
bottom, top, boxmap = compute_gradmaps(binary, scale)
seeds = compute_line_seeds(binary, bottom, top, colseps, scale)
llabels = morph.propagate_labels(boxmap, seeds, conflict=0)
spread = morph.spread_labels(seeds, maxdist=scale)
llabels = np.where(llabels > 0, llabels, spread * binary)
segmentation = llabels * binary
lines = compute_lines(segmentation, scale)
order = reading_order([l.bounds for l in lines])
lsort = topsort(order)
lines = [lines[i].bounds for i in lsort]
return [(s2.start, s1.start, s2.stop, s1.stop) for s1, s2 in lines]
def segment(im, scale=None, black_colseps=False):
"""
Segments a page into text lines.
Segments a page into text lines and returns the absolute coordinates of
each line in reading order.
Args:
im (PIL.Image): A bi-level page of mode '1' or 'L'
scale (float): Scale of the image
black_colseps (bool): Whether column separators are assumed to be
vertical black lines or not
Returns:
[(x1, y1, x2, y2),...]: A list of tuples containing the bounding boxes
of the segmented lines in reading order.
Raises:
KrakenInputException if the input image is not binarized
"""
if im.mode != '1' and not is_bitonal(im):
raise KrakenInputException('Image is not bi-level')
# honestly I've got no idea what's going on here. In theory a simple
# np.array(im, 'i') should suffice here but for some reason the
# tostring/fromstring magic in pil2array alters the array in a way that is
# needed for the algorithm to work correctly.
a = pil2array(im)
binary = np.array(a > 0.5*(np.amin(a) + np.amax(a)), 'i')
binary = 1 - binary
if not scale:
scale = estimate_scale(binary)
binary = remove_hlines(binary, scale)
if black_colseps:
colseps, binary = compute_black_colseps(binary, scale)
else:
colseps = compute_white_colseps(binary, scale)
bottom, top, boxmap = compute_gradmaps(binary, scale)
seeds = compute_line_seeds(binary, bottom, top, colseps, scale)
llabels = morph.propagate_labels(boxmap, seeds, conflict=0)
spread = morph.spread_labels(seeds, maxdist=scale)
llabels = np.where(llabels > 0, llabels, spread*binary)
segmentation = llabels*binary
lines = compute_lines(segmentation, scale)
order = reading_order([l.bounds for l in lines])
lsort = topsort(order)
lines = [lines[i].bounds for i in lsort]
return [(s2.start, s1.start, s2.stop, s1.stop) for s1, s2 in lines]
def transcription(ctx, text_direction, scale, maxcolseps, black_colseps, font,
font_style, prefill, output, images, segment_page):
ti = transcribe.TranscriptionInterface(font, font_style)
if prefill:
logger.info('Loading model {}'.format(prefill))
spin('Loading RNN')
prefill = models.load_any(prefill.encode('utf-8'))
message(u'\b\u2713', fg='green', nl=False)
message('\033[?25h\n', nl=False)
for fp in images:
logger.info('Reading {}'.format(fp.name))
spin('Reading images')
im = Image.open(fp)
if not binarization.is_bitonal(im):
logger.info(u'Binarizing page')
im = binarization.nlbin(im)
if segment_page:
logger.info(u'Segmenting page')
res = pageseg.segment(im, text_direction, scale, maxcolseps,
black_colseps)
else:
res = {
'text_direction': 'horizontal-tb',
'boxes': [(0, 0) + im.size]
}
if prefill:
it = rpred.rpred(prefill, im, res)
preds = []
for pred in it:
logger.info('{}'.format(pred.prediction))
spin('Recognizing')
preds.append(pred)
message(u'\b\u2713', fg='green', nl=False)
message('\033[?25h\n', nl=False)
ti.add_page(im, res, records=preds)
else:
ti.add_page(im, res)
fp.close()
message(u'\b\u2713', fg='green', nl=False)
message('\033[?25h\n', nl=False)
logger.info(u'Writing transcription to {}'.format(output.name))
spin('Writing output')
ti.write(output)
message(u'\b\u2713', fg='green', nl=False)
message('\033[?25h\n', nl=False)
def segment(im,
text_direction='horizontal-lr',
scale=None,
maxcolseps=2,
black_colseps=False):
"""
Segments a page into text lines.
Segments a page into text lines and returns the absolute coordinates of
each line in reading order.
Args:
im (PIL.Image): A bi-level page of mode '1' or 'L'
text_direction (str): Principal direction of the text
(horizontal-lr/rl/vertical-lr/rl)
scale (float): Scale of the image
maxcolseps (int): Maximum number of whitespace column separators
black_colseps (bool): Whether column separators are assumed to be
vertical black lines or not
Returns:
{'text_direction': '$dir', 'boxes': [(x1, y1, x2, y2),...]}: A
dictionary containing the text direction and a list of reading order
sorted bounding boxes under the key 'boxes'.
Raises:
KrakenInputException if the input image is not binarized or the text
direction is invalid.
"""
if im.mode != '1' and not is_bitonal(im):
raise KrakenInputException('Image is not bi-level')
# rotate input image for vertical lines
if text_direction.startswith('horizontal'):
angle = 0
offset = (0, 0)
elif text_direction == 'vertical-lr':
angle = 270
offset = (0, im.size[1])
elif text_direction == 'vertical-rl':
angle = 90
offset = (im.size[0], 0)
else:
raise KrakenInputException('Invalid text direction')
im = im.rotate(angle, expand=True)
# honestly I've got no idea what's going on here. In theory a simple
# np.array(im, 'i') should suffice here but for some reason the
# tostring/fromstring magic in pil2array alters the array in a way that is
# needed for the algorithm to work correctly.
a = pil2array(im)
binary = np.array(a > 0.5 * (np.amin(a) + np.amax(a)), 'i')
binary = 1 - binary
if not scale:
scale = estimate_scale(binary)
binary = remove_hlines(binary, scale)
# emptyish images wll cause exceptions here.
try:
if black_colseps:
colseps, binary = compute_black_colseps(binary, scale, maxcolseps)
else:
colseps = compute_white_colseps(binary, scale, maxcolseps)
except ValueError:
return {'text_direction': text_direction, 'boxes': []}
bottom, top, boxmap = compute_gradmaps(binary, scale)
seeds = compute_line_seeds(binary, bottom, top, colseps, scale)
llabels = morph.propagate_labels(boxmap, seeds, conflict=0)
spread = morph.spread_labels(seeds, maxdist=scale)
llabels = np.where(llabels > 0, llabels, spread * binary)
segmentation = llabels * binary
lines = compute_lines(segmentation, scale)
order = reading_order([l.bounds for l in lines], text_direction[-2:])
lsort = topsort(order)
lines = [lines[i].bounds for i in lsort]
lines = [(s2.start, s1.start, s2.stop, s1.stop) for s1, s2 in lines]
return {
'text_direction': text_direction,
'boxes': rotate_lines(lines, 360 - angle, offset).tolist(),
'script_detection': False
}
def pagexmllineseg(xmlfile,
imgpath,
text_direction='horizontal-lr',
scale=None):
root = etree.parse(xmlfile).getroot()
ns = {"ns": root.nsmap[None]}
# convert point notation from older pagexml versions
for c in root.xpath("//ns:Coords[not(@points)]", namespaces=ns):
cc = []
for point in c.xpath("./ns:Point", namespaces=ns):
# coordstrings = [x.split(",") for x in c.attrib["points"].split()]
cx = point.attrib["x"]
cy = point.attrib["y"]
c.remove(point)
cc.append(cx + "," + cy)
c.attrib["points"] = " ".join(cc)
coordmap = {}
for r in root.xpath('//ns:TextRegion', namespaces=ns):
rid = r.attrib["id"]
coordmap[rid] = {"type": r.attrib["type"]}
coordmap[rid]["coords"] = []
for c in r.xpath("./ns:Coords", namespaces=ns) + r.xpath("./Coords"):
coordmap[rid]["coordstring"] = c.attrib["points"]
coordstrings = [x.split(",") for x in c.attrib["points"].split()]
coordmap[rid]["coords"] += [[int(x[0]), int(x[1])]
for x in coordstrings]
filename = root.xpath('//ns:Page', namespaces=ns)[0]\
.attrib["imageFilename"]
filename = imgpath + "/" + filename
im = Image.open(filename)
for n, c in enumerate(sorted(coordmap)):
if type(scale) == dict:
if coordmap[c]['type'] in scale:
rscale = scale[coordmap[c]['type']]
elif "other" in scale:
rscale = scale["other"]
else:
rscale = None
else:
rscale = scale
coords = coordmap[c]['coords']
if len(coords) < 3:
continue
cropped = cutout(im, coords)
offset = (min([x[0] for x in coords]), min([x[1] for x in coords]))
if cropped is not None:
if not binarization.is_bitonal(cropped):
try:
cropped = binarization.nlbin(cropped)
except SystemError:
continue
if coordmap[c]["type"] == "drop-capital":
lines = [1]
else:
# if line in
lines = segment(cropped,
text_direction=text_direction,
scale=rscale,
maxcolseps=-1)
lines = lines["lines"] if "lines" in lines else []
else:
lines = []
for n, l in enumerate(lines):
if coordmap[c]["type"] == "drop-capital":
coordstrg = coordmap[c]["coordstring"]
else:
coords = ((x[1] + offset[0], x[0] + offset[1])
for x in l.polygon)
coordstrg = " ".join(
[str(x[0]) + "," + str(x[1]) for x in coords])
textregion = root.xpath('//ns:TextRegion[@id="' + c + '"]',
namespaces=ns)[0]
linexml = etree.SubElement(
textregion,
"TextLine",
attrib={"id": "{}_l{:03d}".format(c, n + 1)})
coordsxml = etree.SubElement(linexml,
"Coords",
attrib={"points": coordstrg})
xmlstring = etree.tounicode(root.getroottree()).replace(
"http://schema.primaresearch.org/PAGE/gts/pagecontent/2010-03-19",
"http://schema.primaresearch.org/PAGE/gts/pagecontent/2017-07-15")
no_lines_segm = int(root.xpath("count(//TextLine)"))
return xmlstring, no_lines_segm