def add_page(self, im, segmentation=None, records=None):
"""
Adds an image to the transcription interface, optionally filling in
information from a list of ocr_record objects.
Args:
im (PIL.Image): Input image
records (list): A list of ocr_record objects.
"""
page = {}
fd = BytesIO()
im.save(fd, format='png', optimize=True)
page['index'] = self.page_idx
self.page_idx += 1
page['img'] = 'data:image/png;base64,' + base64.b64encode(fd.getvalue()).decode('ascii')
page['lines'] = []
if records:
for record in records:
splits = regex.split(u'(\s+)', record.prediction)
bbox = max_bbox(record.cuts)
line_offset = 0
segments = []
for segment, whitespace in zip_longest(splits[0::2], splits[1::2]):
if len(segment):
seg_bbox = max_bbox(record.cuts[line_offset:line_offset + len(segment)])
segments.append({'bbox': '{}, {}, {}, {}'.format(*seg_bbox), 'text': segment, 'index': self.seg_idx})
self.seg_idx += 1
line_offset += len(segment)
if whitespace:
line_offset += len(whitespace)
page['lines'].append({'index': self.line_idx, 'recognition': segments,
'left': 100*int(bbox[0]) / im.size[0],
'top': 100*int(bbox[1]) / im.size[1],
'width': 100*(bbox[2] - bbox[0])/im.size[0],
'height': 100*(int(bbox[3]) - int(bbox[1]))/im.size[1],
'bbox': '{}, {}, {}, {}'.format(int(bbox[0]),
int(bbox[1]),
int(bbox[2]),
int(bbox[3]))})
self.line_idx += 1
elif segmentation:
for bbox in segmentation:
page['lines'].append({'index': self.line_idx,
'left': 100*int(bbox[0]) / im.size[0],
'top': 100*int(bbox[1]) / im.size[1],
'width': 100*(bbox[2] - bbox[0])/im.size[0],
'height': 100*(int(bbox[3]) - int(bbox[1]))/im.size[1],
'bbox': '{}, {}, {}, {}'.format(int(bbox[0]),
int(bbox[1]),
int(bbox[2]),
int(bbox[3]))})
self.line_idx += 1
else:
raise KrakenInputException('Neither segmentations nor records given')
self.pages.append(page)
def detect_scripts(im, bounds, model=None):
"""
Detects scripts in a segmented page.
Classifies lines returned by the page segmenter into runs of scripts/writing systems.
Args:
im (PIL.Image): A bi-level page of mode '1' or 'L'
bounds (dict): A dictionary containing a 'boxes' entry with a list of
coordinates (x0, y0, x1, y1) of a text line in the image
and an entry 'text_direction' containing
'horizontal-tb/vertical-lr/rl'.
model (str): Location of the script classification model or None for default.
Returns:
{'text_direction': '$dir', 'boxes': [[(script, (x1, y1, x2, y2)),...]]}: A
dictionary containing the text direction and a list of lists of reading
order sorted bounding boxes under the key 'boxes' with each list
containing the script segmentation of a single line. Script is a
ISO15924 4 character identifier.
Raises:
KrakenInputException if the input image is not binarized or the text
direction is invalid.
KrakenInvalidModelException if no clstm module is available.
"""
if not model:
model = pkg_resources.resource_filename(__name__, 'script.clstm')
rnn = models.load_clstm(model)
# load numerical to 4 char identifier map
with pkg_resources.resource_stream(__name__, 'iso15924.json') as fp:
n2s = json.load(fp)
it = rpred(rnn, im, bounds)
preds = []
for pred in it:
# substitute inherited scripts with neighboring runs
def subs(m, s):
p = u''
for c in s:
if c in m and p:
p += p[-1]
else:
p += c
return p
p = subs([u'\U000f03e6', u'\U000f03e6'], pred.prediction)
# do a reverse run to fix leading inherited scripts
pred.prediction = ''.join(reversed(subs([u'\U000f03e6', u'\U000f03e6'], reversed(p))))
# group by grapheme
t = []
for k, g in groupby(pred, key=lambda x: x[0]):
# convert to ISO15924 numerical identifier
k = ord(k) - 0xF0000
b = max_bbox(x[1] for x in g)
t.append((n2s[str(k)], b))
preds.append(t)
return {'boxes': preds, 'text_direction': bounds['text_direction']}
def detect_scripts(im,
bounds,
model=pkg_resources.resource_filename(
__name__, 'script.mlmodel'),
valid_scripts=None):
"""
Detects scripts in a segmented page.
Classifies lines returned by the page segmenter into runs of scripts/writing systems.
Args:
im (PIL.Image): A bi-level page of mode '1' or 'L'
bounds (dict): A dictionary containing a 'boxes' entry with a list of
coordinates (x0, y0, x1, y1) of a text line in the image
and an entry 'text_direction' containing
'horizontal-lr/rl/vertical-lr/rl'.
model (str): Location of the script classification model or None for default.
valid_scripts (list): List of valid scripts.
Returns:
{'script_detection': True, 'text_direction': '$dir', 'boxes':
[[(script, (x1, y1, x2, y2)),...]]}: A dictionary containing the text
direction and a list of lists of reading order sorted bounding boxes
under the key 'boxes' with each list containing the script segmentation
of a single line. Script is a ISO15924 4 character identifier.
Raises:
KrakenInvalidModelException if no clstm module is available.
"""
raise NotImplementedError(
'Temporarily unavailable. Please open a github ticket if you want this fixed sooner.'
)
im_str = get_im_str(im)
logger.info(u'Detecting scripts with {} in {} lines on {}'.format(
model, len(bounds['boxes']), im_str))
logger.debug(u'Loading detection model {}'.format(model))
rnn = models.load_any(model)
# load numerical to 4 char identifier map
logger.debug(u'Loading label to identifier map')
with pkg_resources.resource_stream(__name__, 'iso15924.json') as fp:
n2s = json.load(fp)
# convert allowed scripts to labels
val_scripts = []
if valid_scripts:
logger.debug(
u'Converting allowed scripts list {}'.format(valid_scripts))
for k, v in n2s.items():
if v in valid_scripts:
val_scripts.append(chr(int(k) + 0xF0000))
else:
valid_scripts = []
it = rpred(rnn, im, bounds, bidi_reordering=False)
preds = []
logger.debug(u'Running detection')
for pred, bbox in zip(it, bounds['boxes']):
# substitute inherited scripts with neighboring runs
def _subs(m, s, r=False):
p = u''
for c in s:
if c in m and p and not r:
p += p[-1]
elif c not in m and p and r:
p += p[-1]
else:
p += c
return p
logger.debug(u'Substituting scripts')
p = _subs([u'\U000f03e2', u'\U000f03e6'], pred.prediction)
# do a reverse run to fix leading inherited scripts
pred.prediction = ''.join(
reversed(_subs([u'\U000f03e2', u'\U000f03e6'], reversed(p))))
# group by valid scripts. two steps: 1. substitute common confusions
# (Latin->Fraktur and Syriac->Arabic) if given in script list.
if 'Arab' in valid_scripts and 'Syrc' not in valid_scripts:
pred.prediction = pred.prediction.replace(u'\U000f0087',
u'\U000f00a0')
if 'Latn' in valid_scripts and 'Latf' not in valid_scripts:
pred.prediction = pred.prediction.replace(u'\U000f00d9',
u'\U000f00d7')
# next merge adjacent scripts
if val_scripts:
pred.prediction = _subs(val_scripts, pred.prediction, r=True)
# group by grapheme
t = []
logger.debug(u'Merging detections')
# if line contains only a single script return whole line bounding box
if len(set(pred.prediction)) == 1:
logger.debug('Only one script on line. Emitting whole line bbox')
k = ord(pred.prediction[0]) - 0xF0000
t.append((n2s[str(k)], bbox))
else:
for k, g in groupby(pred, key=lambda x: x[0]):
# convert to ISO15924 numerical identifier
k = ord(k) - 0xF0000
b = max_bbox(x[1] for x in g)
t.append((n2s[str(k)], b))
preds.append(t)
return {
'boxes': preds,
'text_direction': bounds['text_direction'],
'script_detection': True
}
def detect_scripts(im, bounds, model=pkg_resources.resource_filename(__name__, 'script.mlmodel'), valid_scripts=None):
"""
Detects scripts in a segmented page.
Classifies lines returned by the page segmenter into runs of scripts/writing systems.
Args:
im (PIL.Image): A bi-level page of mode '1' or 'L'
bounds (dict): A dictionary containing a 'boxes' entry with a list of
coordinates (x0, y0, x1, y1) of a text line in the image
and an entry 'text_direction' containing
'horizontal-lr/rl/vertical-lr/rl'.
model (str): Location of the script classification model or None for default.
valid_scripts (list): List of valid scripts.
Returns:
{'script_detection': True, 'text_direction': '$dir', 'boxes':
[[(script, (x1, y1, x2, y2)),...]]}: A dictionary containing the text
direction and a list of lists of reading order sorted bounding boxes
under the key 'boxes' with each list containing the script segmentation
of a single line. Script is a ISO15924 4 character identifier.
Raises:
KrakenInvalidModelException if no clstm module is available.
"""
raise NotImplementedError('Temporarily unavailable. Please open a github ticket if you want this fixed sooner.')
im_str = get_im_str(im)
logger.info(u'Detecting scripts with {} in {} lines on {}'.format(model, len(bounds['boxes']), im_str))
logger.debug(u'Loading detection model {}'.format(model))
rnn = models.load_any(model)
# load numerical to 4 char identifier map
logger.debug(u'Loading label to identifier map')
with pkg_resources.resource_stream(__name__, 'iso15924.json') as fp:
n2s = json.load(fp)
# convert allowed scripts to labels
val_scripts = []
if valid_scripts:
logger.debug(u'Converting allowed scripts list {}'.format(valid_scripts))
for k, v in n2s.items():
if v in valid_scripts:
val_scripts.append(chr(int(k) + 0xF0000))
else:
valid_scripts = []
it = rpred(rnn, im, bounds, bidi_reordering=False)
preds = []
logger.debug(u'Running detection')
for pred, bbox in zip(it, bounds['boxes']):
# substitute inherited scripts with neighboring runs
def _subs(m, s, r=False):
p = u''
for c in s:
if c in m and p and not r:
p += p[-1]
elif c not in m and p and r:
p += p[-1]
else:
p += c
return p
logger.debug(u'Substituting scripts')
p = _subs([u'\U000f03e2', u'\U000f03e6'], pred.prediction)
# do a reverse run to fix leading inherited scripts
pred.prediction = ''.join(reversed(_subs([u'\U000f03e2', u'\U000f03e6'], reversed(p))))
# group by valid scripts. two steps: 1. substitute common confusions
# (Latin->Fraktur and Syriac->Arabic) if given in script list.
if 'Arab' in valid_scripts and 'Syrc' not in valid_scripts:
pred.prediction = pred.prediction.replace(u'\U000f0087', u'\U000f00a0')
if 'Latn' in valid_scripts and 'Latf' not in valid_scripts:
pred.prediction = pred.prediction.replace(u'\U000f00d9', u'\U000f00d7')
# next merge adjacent scripts
if val_scripts:
pred.prediction = _subs(val_scripts, pred.prediction, r=True)
# group by grapheme
t = []
logger.debug(u'Merging detections')
# if line contains only a single script return whole line bounding box
if len(set(pred.prediction)) == 1:
logger.debug('Only one script on line. Emitting whole line bbox')
k = ord(pred.prediction[0]) - 0xF0000
t.append((n2s[str(k)], bbox))
else:
for k, g in groupby(pred, key=lambda x: x[0]):
# convert to ISO15924 numerical identifier
k = ord(k) - 0xF0000
b = max_bbox(x[1] for x in g)
t.append((n2s[str(k)], b))
preds.append(t)
return {'boxes': preds, 'text_direction': bounds['text_direction'], 'script_detection': True}