def process(self):
"""
Performs the line segmentation.
"""
with PyTessBaseAPI(
psm=PSM.SINGLE_LINE,
path=TESSDATA_PREFIX,
) as tessapi:
for (n, input_file) in enumerate(self.input_files):
pcgts = page_from_file(self.workspace.download_file(input_file))
image_url = pcgts.get_Page().imageFilename
for region in pcgts.get_Page().get_TextRegion():
for line in region.get_TextLine():
log.debug("Detecting words in line '%s'", line.id)
image = self.workspace.resolve_image_as_pil(image_url, polygon_from_points(line.get_Coords().points))
tessapi.SetImage(image)
offset = xywh_from_points(line.get_Coords().points)
for (word_no, component) in enumerate(tessapi.GetComponentImages(RIL.WORD, True)):
word_id = '%s_word%04d' % (line.id, word_no)
word_xywh = component[1]
word_xywh['x'] += offset['x']
word_xywh['y'] += offset['y']
line.add_Word(WordType(id=word_id, Coords=CoordsType(points_from_xywh(word_xywh))))
ID = concat_padded(self.output_file_grp, n)
self.workspace.add_file(
ID=ID,
file_grp=self.output_file_grp,
local_filename='%s/%s' % (self.output_file_grp, ID),
mimetype=MIMETYPE_PAGE,
content=to_xml(pcgts).encode('utf-8'),
)
def _merge_word_nodes(self, nodes):
if not nodes:
LOG.error('nothing to merge')
return None
merged = WordType()
merged.set_id(','.join([n.id for n in nodes]))
points = ' '.join([n.get_Coords().points for n in nodes])
if points:
merged.set_Coords(nodes[0].get_Coords()) # TODO merge
# make other attributes and TextStyle a majority vote, but no Glyph
# (too fine-grained) or TextEquiv (overwritten from best path anyway)
languages = list(map(lambda elem: elem.get_language(), nodes))
if languages:
merged.set_language(max(set(languages), key=languages.count))
# TODO other attributes...
styles = map(lambda elem: elem.get_TextStyle(), nodes)
if any(styles):
# TODO make a majority vote on each attribute here
merged.set_TextStyle(nodes[0].get_TextStyle())
return merged
def test_alternative_image_additions():
pcgts = PcGtsType(pcGtsId="foo")
assert pcgts.pcGtsId == 'foo'
# act
# Page/AlternativeImage
page = PageType()
pcgts.set_Page(page)
page.add_AlternativeImage(AlternativeImageType())
# TextRegion/AlternativeImage
region = TextRegionType()
page.add_TextRegion(region)
region.add_AlternativeImage(AlternativeImageType())
# TextLine/AlternativeImage
line = TextLineType()
region.add_TextLine(line)
line.add_AlternativeImage(AlternativeImageType())
# Word/AlternativeImage
word = WordType()
line.add_Word(word)
word.add_AlternativeImage(AlternativeImageType())
# Glyph/AlternativeImage
glyph = GlyphType()
word.add_Glyph(glyph)
glyph.add_AlternativeImage(AlternativeImageType())
def _process_words_in_line(self, result_it, line, line_xywh):
LOG = getLogger('processor.TesserocrRecognize')
if not result_it or result_it.Empty(RIL.WORD):
LOG.warning("No text in line '%s'", line.id)
return
# iterate until IsAtFinalElement(RIL.LINE, RIL.WORD):
word_no = 0
while result_it and not result_it.Empty(RIL.WORD):
word_id = '%s_word%04d' % (line.id, word_no)
LOG.debug("Decoding text in word '%s'", word_id)
bbox = result_it.BoundingBox(RIL.WORD)
# convert to absolute coordinates:
polygon = coordinates_for_segment(polygon_from_x0y0x1y1(bbox),
None, line_xywh) - self.parameter['padding']
polygon2 = polygon_for_parent(polygon, line)
if polygon2 is not None:
polygon = polygon2
points = points_from_polygon(polygon)
word = WordType(id=word_id, Coords=CoordsType(points))
if polygon2 is None:
# could happen due to rotation
LOG.info('Ignoring extant word: %s', points)
else:
line.add_Word(word)
# todo: determine if font attributes available for word level will work with LSTM models
word_attributes = result_it.WordFontAttributes()
if word_attributes:
word_style = TextStyleType(
fontSize=word_attributes['pointsize']
if 'pointsize' in word_attributes else None,
fontFamily=word_attributes['font_name']
if 'font_name' in word_attributes else None,
bold=word_attributes['bold']
if 'bold' in word_attributes else None,
italic=word_attributes['italic']
if 'italic' in word_attributes else None,
underlined=word_attributes['underlined']
if 'underlined' in word_attributes else None,
monospace=word_attributes['monospace']
if 'monospace' in word_attributes else None,
serif=word_attributes['serif']
if 'serif' in word_attributes else None)
word.set_TextStyle(word_style) # (or somewhere in custom attribute?)
# add word annotation unconditionally (i.e. even for glyph level):
word.add_TextEquiv(TextEquivType(
Unicode=result_it.GetUTF8Text(RIL.WORD),
conf=result_it.Confidence(RIL.WORD)/100))
if self.parameter['textequiv_level'] != 'word':
self._process_glyphs_in_word(result_it, word, line_xywh)
if result_it.IsAtFinalElement(RIL.TEXTLINE, RIL.WORD):
break
else:
word_no += 1
result_it.Next(RIL.WORD)
def test_alternativeImage(self):
pcgts = PcGtsType(pcGtsId="foo")
self.assertEqual(pcgts.pcGtsId, 'foo')
# Page/AlternativeImage
page = PageType()
pcgts.set_Page(page)
page.add_AlternativeImage(AlternativeImageType())
# TextRegion/AlternativeImage
region = TextRegionType()
page.add_TextRegion(region)
region.add_AlternativeImage(AlternativeImageType())
# TextLine/AlternativeImage
line = TextLineType()
region.add_TextLine(line)
line.add_AlternativeImage(AlternativeImageType())
# Word/AlternativeImage
word = WordType()
line.add_Word(word)
word.add_AlternativeImage(AlternativeImageType())
# Glyph/AlternativeImage
glyph = GlyphType()
word.add_Glyph(glyph)
glyph.add_AlternativeImage(AlternativeImageType())
def process(self):
"""
Performs the recognition.
"""
assert_file_grp_cardinality(self.input_file_grp, 1)
assert_file_grp_cardinality(self.output_file_grp, 1)
self._init_calamari()
for (n, input_file) in enumerate(self.input_files):
page_id = input_file.pageId or input_file.ID
log.info("INPUT FILE %i / %s", n, page_id)
pcgts = page_from_file(self.workspace.download_file(input_file))
page = pcgts.get_Page()
page_image, page_xywh, page_image_info = self.workspace.image_from_page(
page, page_id)
for region in pcgts.get_Page().get_TextRegion():
region_image, region_xywh = self.workspace.image_from_segment(
region, page_image, page_xywh)
textlines = region.get_TextLine()
log.info("About to recognize %i lines of region '%s'",
len(textlines), region.id)
for (line_no, line) in enumerate(textlines):
log.debug("Recognizing line '%s' in region '%s'", line.id,
region.id)
line_image, line_coords = self.workspace.image_from_segment(
line, region_image, region_xywh)
line_image_np = np.array(line_image, dtype=np.uint8)
raw_results = list(
self.predictor.predict_raw([line_image_np],
progress_bar=False))[0]
for i, p in enumerate(raw_results):
p.prediction.id = "fold_{}".format(i)
prediction = self.voter.vote_prediction_result(raw_results)
prediction.id = "voted"
# Build line text on our own
#
# Calamari does whitespace post-processing on prediction.sentence, while it does not do the same
# on prediction.positions. Do it on our own to have consistency.
#
# XXX Check Calamari's built-in post-processing on prediction.sentence
def _sort_chars(p):
"""Filter and sort chars of prediction p"""
chars = p.chars
chars = [
c for c in chars if c.char
] # XXX Note that omission probabilities are not normalized?!
chars = [
c for c in chars if c.probability >=
self.parameter['glyph_conf_cutoff']
]
chars = sorted(chars,
key=lambda k: k.probability,
reverse=True)
return chars
def _drop_leading_spaces(positions):
return list(
itertools.dropwhile(
lambda p: _sort_chars(p)[0].char == " ",
positions))
def _drop_trailing_spaces(positions):
return list(
reversed(_drop_leading_spaces(
reversed(positions))))
def _drop_double_spaces(positions):
def _drop_double_spaces_generator(positions):
last_was_space = False
for p in positions:
if p.chars[0].char == " ":
if not last_was_space:
yield p
last_was_space = True
else:
yield p
last_was_space = False
return list(_drop_double_spaces_generator(positions))
positions = prediction.positions
positions = _drop_leading_spaces(positions)
positions = _drop_trailing_spaces(positions)
positions = _drop_double_spaces(positions)
positions = list(positions)
line_text = ''.join(
_sort_chars(p)[0].char for p in positions)
if line_text != prediction.sentence:
log.warning(
"Our own line text is not the same as Calamari's: '%s' != '%s'",
line_text, prediction.sentence)
# Delete existing results
if line.get_TextEquiv():
log.warning("Line '%s' already contained text results",
line.id)
line.set_TextEquiv([])
if line.get_Word():
log.warning(
"Line '%s' already contained word segmentation",
line.id)
line.set_Word([])
# Save line results
line_conf = prediction.avg_char_probability
line.set_TextEquiv(
[TextEquivType(Unicode=line_text, conf=line_conf)])
# Save word results
#
# Calamari OCR does not provide word positions, so we infer word positions from a. text segmentation
# and b. the glyph positions. This is necessary because the PAGE XML format enforces a strict
# hierarchy of lines > words > glyphs.
def _words(s):
"""Split words based on spaces and include spaces as 'words'"""
spaces = None
word = ''
for c in s:
if c == ' ' and spaces is True:
word += c
elif c != ' ' and spaces is False:
word += c
else:
if word:
yield word
word = c
spaces = (c == ' ')
yield word
if self.parameter['textequiv_level'] in ['word', 'glyph']:
word_no = 0
i = 0
for word_text in _words(line_text):
word_length = len(word_text)
if not all(c == ' ' for c in word_text):
word_positions = positions[i:i + word_length]
word_start = word_positions[0].global_start
word_end = word_positions[-1].global_end
polygon = polygon_from_x0y0x1y1([
word_start, 0, word_end, line_image.height
])
points = points_from_polygon(
coordinates_for_segment(
polygon, None, line_coords))
# XXX Crop to line polygon?
word = WordType(id='%s_word%04d' %
(line.id, word_no),
Coords=CoordsType(points))
word.add_TextEquiv(
TextEquivType(Unicode=word_text))
if self.parameter[
'textequiv_level'] == 'glyph':
for glyph_no, p in enumerate(
word_positions):
glyph_start = p.global_start
glyph_end = p.global_end
polygon = polygon_from_x0y0x1y1([
glyph_start, 0, glyph_end,
line_image.height
])
points = points_from_polygon(
coordinates_for_segment(
polygon, None, line_coords))
glyph = GlyphType(
id='%s_glyph%04d' %
(word.id, glyph_no),
Coords=CoordsType(points))
# Add predictions (= TextEquivs)
char_index_start = 1 # Must start with 1, see https://ocr-d.github.io/page#multiple-textequivs
for char_index, char in enumerate(
_sort_chars(p),
start=char_index_start):
glyph.add_TextEquiv(
TextEquivType(
Unicode=char.char,
index=char_index,
conf=char.probability))
word.add_Glyph(glyph)
line.add_Word(word)
word_no += 1
i += word_length
_page_update_higher_textequiv_levels('line', pcgts)
# Add metadata about this operation and its runtime parameters:
metadata = pcgts.get_Metadata() # ensured by from_file()
metadata.add_MetadataItem(
MetadataItemType(
type_="processingStep",
name=self.ocrd_tool['steps'][0],
value=TOOL,
Labels=[
LabelsType(externalModel="ocrd-tool",
externalId="parameters",
Label=[
LabelType(type_=name,
value=self.parameter[name])
for name in self.parameter.keys()
])
]))
file_id = make_file_id(input_file, self.output_file_grp)
pcgts.set_pcGtsId(file_id)
self.workspace.add_file(ID=file_id,
file_grp=self.output_file_grp,
pageId=input_file.pageId,
mimetype=MIMETYPE_PAGE,
local_filename=os.path.join(
self.output_file_grp,
file_id + '.xml'),
content=to_xml(pcgts))
def process(self):
"""Performs word segmentation with Tesseract on the workspace.
Open and deserialize PAGE input files and their respective images,
then iterate over the element hierarchy down to the textline level,
and remove any existing Word elements (unless ``overwrite_words``
is False).
Set up Tesseract to detect words, and add each one to the line
at the detected coordinates.
Produce a new output file by serialising the resulting hierarchy.
"""
LOG = getLogger('processor.TesserocrSegmentWord')
assert_file_grp_cardinality(self.input_file_grp, 1)
assert_file_grp_cardinality(self.output_file_grp, 1)
overwrite_words = self.parameter['overwrite_words']
with PyTessBaseAPI(
psm=PSM.SINGLE_LINE,
path=TESSDATA_PREFIX
) as tessapi:
for (n, input_file) in enumerate(self.input_files):
page_id = input_file.pageId or input_file.ID
LOG.info("INPUT FILE %i / %s", n, page_id)
pcgts = page_from_file(self.workspace.download_file(input_file))
self.add_metadata(pcgts)
page = pcgts.get_Page()
page_image, page_coords, page_image_info = self.workspace.image_from_page(
page, page_id)
if self.parameter['dpi'] > 0:
dpi = self.parameter['dpi']
LOG.info("Page '%s' images will use %d DPI from parameter override", page_id, dpi)
elif page_image_info.resolution != 1:
dpi = page_image_info.resolution
if page_image_info.resolutionUnit == 'cm':
dpi = round(dpi * 2.54)
LOG.info("Page '%s' images will use %d DPI from image meta-data", page_id, dpi)
else:
dpi = 0
LOG.info("Page '%s' images will use DPI estimated from segmentation", page_id)
if dpi:
tessapi.SetVariable('user_defined_dpi', str(dpi))
for region in page.get_TextRegion():
region_image, region_coords = self.workspace.image_from_segment(
region, page_image, page_coords)
for line in region.get_TextLine():
if line.get_Word():
if overwrite_words:
LOG.info('removing existing Words in line "%s"', line.id)
line.set_Word([])
else:
LOG.warning('keeping existing Words in line "%s"', line.id)
LOG.debug("Detecting words in line '%s'", line.id)
line_image, line_coords = self.workspace.image_from_segment(
line, region_image, region_coords)
tessapi.SetImage(line_image)
for word_no, component in enumerate(tessapi.GetComponentImages(RIL.WORD, True, raw_image=True)):
word_id = '%s_word%04d' % (line.id, word_no)
word_polygon = polygon_from_xywh(component[1])
word_polygon = coordinates_for_segment(word_polygon, line_image, line_coords)
word_polygon2 = polygon_for_parent(word_polygon, line)
if word_polygon2 is not None:
word_polygon = word_polygon2
word_points = points_from_polygon(word_polygon)
if word_polygon2 is None:
# could happen due to rotation
LOG.info('Ignoring extant word: %s', word_points)
continue
line.add_Word(WordType(
id=word_id, Coords=CoordsType(word_points)))
file_id = make_file_id(input_file, self.output_file_grp)
pcgts.set_pcGtsId(file_id)
self.workspace.add_file(
ID=file_id,
file_grp=self.output_file_grp,
pageId=input_file.pageId,
mimetype=MIMETYPE_PAGE,
local_filename=os.path.join(self.output_file_grp,
file_id + '.xml'),
content=to_xml(pcgts))
def process(self):
"""
Perform text recognition with Calamari on the workspace.
If ``texequiv_level`` is ``word`` or ``glyph``, then additionally create word / glyph level segments by
splitting at white space characters / glyph boundaries. In the case of ``glyph``, add all alternative character
hypotheses down to ``glyph_conf_cutoff`` confidence threshold.
"""
log = getLogger('processor.CalamariRecognize')
assert_file_grp_cardinality(self.input_file_grp, 1)
assert_file_grp_cardinality(self.output_file_grp, 1)
for (n, input_file) in enumerate(self.input_files):
page_id = input_file.pageId or input_file.ID
log.info("INPUT FILE %i / %s", n, page_id)
pcgts = page_from_file(self.workspace.download_file(input_file))
page = pcgts.get_Page()
page_image, page_coords, page_image_info = self.workspace.image_from_page(
page, page_id, feature_selector=self.features)
for region in page.get_AllRegions(classes=['Text']):
region_image, region_coords = self.workspace.image_from_segment(
region,
page_image,
page_coords,
feature_selector=self.features)
textlines = region.get_TextLine()
log.info("About to recognize %i lines of region '%s'",
len(textlines), region.id)
line_images_np = []
line_coordss = []
for line in textlines:
log.debug("Recognizing line '%s' in region '%s'", line.id,
region.id)
line_image, line_coords = self.workspace.image_from_segment(
line,
region_image,
region_coords,
feature_selector=self.features)
if ('binarized' not in line_coords['features']
and 'grayscale_normalized'
not in line_coords['features']
and self.network_input_channels == 1):
# We cannot use a feature selector for this since we don't
# know whether the model expects (has been trained on)
# binarized or grayscale images; but raw images are likely
# always inadequate:
log.warning(
"Using raw image for line '%s' in region '%s'",
line.id, region.id)
line_image = line_image if all(line_image.size) else [[0]]
line_image_np = np.array(line_image, dtype=np.uint8)
line_images_np.append(line_image_np)
line_coordss.append(line_coords)
raw_results_all = self.predictor.predict_raw(
line_images_np, progress_bar=False)
for line, line_coords, raw_results in zip(
textlines, line_coordss, raw_results_all):
for i, p in enumerate(raw_results):
p.prediction.id = "fold_{}".format(i)
prediction = self.voter.vote_prediction_result(raw_results)
prediction.id = "voted"
# Build line text on our own
#
# Calamari does whitespace post-processing on prediction.sentence, while it does not do the same
# on prediction.positions. Do it on our own to have consistency.
#
# XXX Check Calamari's built-in post-processing on prediction.sentence
def _sort_chars(p):
"""Filter and sort chars of prediction p"""
chars = p.chars
chars = [
c for c in chars if c.char
] # XXX Note that omission probabilities are not normalized?!
chars = [
c for c in chars if c.probability >=
self.parameter['glyph_conf_cutoff']
]
chars = sorted(chars,
key=lambda k: k.probability,
reverse=True)
return chars
def _drop_leading_spaces(positions):
return list(
itertools.dropwhile(
lambda p: _sort_chars(p)[0].char == " ",
positions))
def _drop_trailing_spaces(positions):
return list(
reversed(_drop_leading_spaces(
reversed(positions))))
def _drop_double_spaces(positions):
def _drop_double_spaces_generator(positions):
last_was_space = False
for p in positions:
if p.chars[0].char == " ":
if not last_was_space:
yield p
last_was_space = True
else:
yield p
last_was_space = False
return list(_drop_double_spaces_generator(positions))
positions = prediction.positions
positions = _drop_leading_spaces(positions)
positions = _drop_trailing_spaces(positions)
positions = _drop_double_spaces(positions)
positions = list(positions)
line_text = ''.join(
_sort_chars(p)[0].char for p in positions)
if line_text != prediction.sentence:
log.warning(
"Our own line text is not the same as Calamari's: '%s' != '%s'",
line_text, prediction.sentence)
# Delete existing results
if line.get_TextEquiv():
log.warning("Line '%s' already contained text results",
line.id)
line.set_TextEquiv([])
if line.get_Word():
log.warning(
"Line '%s' already contained word segmentation",
line.id)
line.set_Word([])
# Save line results
line_conf = prediction.avg_char_probability
line.set_TextEquiv(
[TextEquivType(Unicode=line_text, conf=line_conf)])
# Save word results
#
# Calamari OCR does not provide word positions, so we infer word positions from a. text segmentation
# and b. the glyph positions. This is necessary because the PAGE XML format enforces a strict
# hierarchy of lines > words > glyphs.
def _words(s):
"""Split words based on spaces and include spaces as 'words'"""
spaces = None
word = ''
for c in s:
if c == ' ' and spaces is True:
word += c
elif c != ' ' and spaces is False:
word += c
else:
if word:
yield word
word = c
spaces = (c == ' ')
yield word
if self.parameter['textequiv_level'] in ['word', 'glyph']:
word_no = 0
i = 0
for word_text in _words(line_text):
word_length = len(word_text)
if not all(c == ' ' for c in word_text):
word_positions = positions[i:i + word_length]
word_start = word_positions[0].global_start
word_end = word_positions[-1].global_end
polygon = polygon_from_x0y0x1y1([
word_start, 0, word_end, line_image.height
])
points = points_from_polygon(
coordinates_for_segment(
polygon, None, line_coords))
# XXX Crop to line polygon?
word = WordType(id='%s_word%04d' %
(line.id, word_no),
Coords=CoordsType(points))
word.add_TextEquiv(
TextEquivType(Unicode=word_text))
if self.parameter[
'textequiv_level'] == 'glyph':
for glyph_no, p in enumerate(
word_positions):
glyph_start = p.global_start
glyph_end = p.global_end
polygon = polygon_from_x0y0x1y1([
glyph_start, 0, glyph_end,
line_image.height
])
points = points_from_polygon(
coordinates_for_segment(
polygon, None, line_coords))
glyph = GlyphType(
id='%s_glyph%04d' %
(word.id, glyph_no),
Coords=CoordsType(points))
# Add predictions (= TextEquivs)
char_index_start = 1 # Must start with 1, see https://ocr-d.github.io/page#multiple-textequivs
for char_index, char in enumerate(
_sort_chars(p),
start=char_index_start):
glyph.add_TextEquiv(
TextEquivType(
Unicode=char.char,
index=char_index,
conf=char.probability))
word.add_Glyph(glyph)
line.add_Word(word)
word_no += 1
i += word_length
_page_update_higher_textequiv_levels('line', pcgts)
# Add metadata about this operation and its runtime parameters:
self.add_metadata(pcgts)
file_id = make_file_id(input_file, self.output_file_grp)
pcgts.set_pcGtsId(file_id)
self.workspace.add_file(ID=file_id,
file_grp=self.output_file_grp,
pageId=input_file.pageId,
mimetype=MIMETYPE_PAGE,
local_filename=os.path.join(
self.output_file_grp,
file_id + '.xml'),
content=to_xml(pcgts))
def process_lines(self, textlines, predfiles, fgrp, regionid):
for line in textlines:
for file in predfiles:
if file == '-'.join([fgrp, regionid, line.id]):
self.log.info("Processing text in line '%s'", line.id)
filepath = self.root + '/' + file + '.json'
with open(filepath) as f:
data = json.load(f)
linepred = data['predictions'][0]['sentence']
line_conf = []
line_pos = []
w = ''
word_conf = []
words = []
word_pos = []
positions = data['predictions'][0]['positions']
for i, d in enumerate(positions):
char = d['chars'][0]['char']
char_conf = d['chars'][0]['probability']
char_pos = (d['globalStart'], d['globalEnd'])
if char == ' ':
words.append(w)
w = ''
line_conf.append(word_conf)
word_conf = []
line_pos.append(word_pos)
word_pos = []
else:
w += char
word_conf.append(char_conf)
word_pos.append(char_pos)
if i == len(positions) - 1:
words.append(w)
line_conf.append(word_conf)
line_pos.append(word_pos)
wconfs = [(min(conf) + max(conf)) / 2
for conf in line_conf]
lineconf = (min(wconfs) + max(wconfs)) / 2
line.replace_TextEquiv_at(
0,
TextEquivType(Unicode=linepred,
conf=str(lineconf)))
if self.maxlevel == 'word' or 'glyph':
box = bounding_box(line.get_Coords().points)
line.Word = []
for w_no, w in enumerate(words):
# Coords of word
wordbounding = (line_pos[w_no][0][0],
line_pos[w_no][-1][-1])
word_bbox = [
box[0] + wordbounding[0], box[1],
box[2] + wordbounding[1], box[3]
]
word_id = '%s_word%04d' % (line.id, w_no)
word = WordType(
id=word_id,
Coords=CoordsType(
points_from_x0y0x1y1(word_bbox)))
line.add_Word(word)
word.add_TextEquiv(
TextEquivType(Unicode=w,
conf=str(wconfs[w_no])))
if self.maxlevel == 'glyph':
for glyph_no, g in enumerate(w):
glyphbounding = (
line_pos[w_no][glyph_no][0],
line_pos[w_no][glyph_no][-1])
glyph_bbox = [
box[0] + glyphbounding[0], box[1],
box[2] + glyphbounding[1], box[3]
]
glyph_id = '%s_glyph%04d' % (word.id,
glyph_no)
glyph = GlyphType(
id=glyph_id,
Coords=CoordsType(
points_from_x0y0x1y1(
glyph_bbox)))
word.add_Glyph(glyph)
glyph.add_TextEquiv(
TextEquivType(
Unicode=g,
conf=str(line_conf[w_no]
[glyph_no])))
def _split_word_at_space(word):
prev_ = WordType(id=word.id + '_l')
next_ = WordType(id=word.id + '_r')
xywh = xywh_from_points(word.get_Coords().points)
textequiv = word.get_TextEquiv()[0]
pos = textequiv.Unicode.index(" ")
fract = pos / len(textequiv.Unicode)
xywh_prev = xywh.copy()
xywh_prev.update({'w': xywh['w'] * fract})
prev_.set_Coords(CoordsType(points=points_from_xywh(xywh_prev)))
xywh_next = xywh.copy()
xywh_next.update({
'x': xywh['x'] + xywh['w'] * fract,
'w': xywh['w'] * (1 - fract)
})
next_.set_Coords(CoordsType(points=points_from_xywh(xywh_next)))
if word.get_language():
prev_.set_language(word.get_language())
next_.set_language(word.get_language())
if word.get_TextStyle():
prev_.set_TextStyle(word.get_TextStyle())
next_.set_TextStyle(word.get_TextStyle())
# Glyphs: irrelevant at this processing level
textequiv_prev = TextEquivType(Unicode=textequiv.Unicode[0:pos],
conf=textequiv.conf)
textequiv_next = TextEquivType(Unicode=textequiv.Unicode[pos + 1:],
conf=textequiv.conf)
prev_.set_TextEquiv([textequiv_prev])
next_.set_TextEquiv([textequiv_next])
return prev_, next_
def _split_word_at_glyph(word, glyph):
prev_ = WordType(id=word.id + '_l')
next_ = WordType(id=word.id + '_r')
xywh_glyph = xywh_from_points(glyph.get_Coords().points)
xywh_word = xywh_from_points(word.get_Coords().points)
xywh_prev = xywh_word.copy()
xywh_prev.update({'w': xywh_glyph['x'] - xywh_word['x']})
prev_.set_Coords(CoordsType(points=points_from_xywh(xywh_prev)))
xywh_next = xywh_word.copy()
xywh_next.update({
'x': xywh_glyph['x'] - xywh_glyph['w'],
'w': xywh_word['w'] - xywh_prev['w']
})
next_.set_Coords(CoordsType(points=points_from_xywh(xywh_next)))
if word.get_language():
prev_.set_language(word.get_language())
next_.set_language(word.get_language())
if word.get_TextStyle():
prev_.set_TextStyle(word.get_TextStyle())
next_.set_TextStyle(word.get_TextStyle())
glyphs = word.get_Glyph()
pos = glyphs.index(glyph)
prev_.set_Glyph(glyphs[0:pos])
next_.set_Glyph(glyphs[pos + 1:])
# TextEquiv: will be overwritten by page_update_higher_textequiv_levels
return prev_, next_
def _merge_words(prev_, next_):
merged = WordType(id=prev_.id + '.' + next_.id)
merged.set_Coords(
CoordsType(points=points_from_xywh(
xywh_from_points(prev_.get_Coords().points + ' ' +
next_.get_Coords().points))))
if prev_.get_language():
merged.set_language(prev_.get_language())
if prev_.get_TextStyle():
merged.set_TextStyle(prev_.get_TextStyle())
if prev_.get_Glyph() or next_.get_Glyph():
merged.set_Glyph(prev_.get_Glyph() + next_.get_Glyph())
if prev_.get_TextEquiv():
merged.set_TextEquiv(prev_.get_TextEquiv())
else:
merged.set_TextEquiv([TextEquivType(Unicode='', conf=1.0)])
if next_.get_TextEquiv():
textequiv = merged.get_TextEquiv()[0]
textequiv2 = next_.get_TextEquiv()[0]
textequiv.Unicode += textequiv2.Unicode
if textequiv.conf and textequiv2.conf:
textequiv.conf *= textequiv2.conf
return merged
def process_lines(self, textlines, maxlevel, region_image, region_coords):
edits = 0
lengs = 0
for line in textlines:
line_image, line_coords = self.workspace.image_from_segment(
line, region_image, region_coords)
self.logger.info("Recognizing text in line '%s'", line.id)
if line.get_TextEquiv():
linegt = line.TextEquiv[0].Unicode
else:
linegt = ''
self.logger.debug("GT '%s': '%s'", line.id, linegt)
# remove existing annotation below line level:
line.set_TextEquiv([])
line.set_Word([])
if line_image.size[1] < 16:
self.logger.debug(
"ERROR: bounding box is too narrow at line %s", line.id)
continue
# resize image to 48 pixel height
final_img, scale = resize_keep_ratio(line_image)
# process ocropy:
try:
linepred, clist, rlist, confidlist = recognize(final_img,
self.pad,
self.network,
check=True)
except Exception as err:
self.logger.debug('error processing line "%s": %s', line.id,
err)
continue
self.logger.debug("OCR '%s': '%s'", line.id, linepred)
edits += Levenshtein.distance(linepred, linegt)
lengs += len(linegt)
words = [x.strip() for x in linepred.split(' ') if x.strip()]
word_r_list = [[0]] # r-positions of every glyph in every word
word_conf_list = [[]] # confidences of every glyph in every word
if words != []:
w_no = 0
found_char = False
for i, c in enumerate(clist):
if c != ' ':
found_char = True
word_conf_list[w_no].append(confidlist[i])
word_r_list[w_no].append(rlist[i])
if c == ' ' and found_char:
if i == 0:
word_r_list[0][0] = rlist[i]
elif i + 1 <= len(clist) - 1 and clist[i + 1] != ' ':
word_conf_list.append([])
word_r_list.append([rlist[i]])
w_no += 1
else:
word_conf_list = [[0]]
word_r_list = [[0, line_image.width]]
# conf for each word
wordsconf = [(min(x) + max(x)) / 2 for x in word_conf_list]
# conf for the line
line_conf = (min(wordsconf) + max(wordsconf)) / 2
# line text
line.add_TextEquiv(TextEquivType(Unicode=linepred, conf=line_conf))
if maxlevel in ['word', 'glyph']:
for word_no, word_str in enumerate(words):
word_points = points_from_polygon(
coordinates_for_segment(
np.array(
polygon_from_bbox(
word_r_list[word_no][0] / scale, 0,
word_r_list[word_no][-1] / scale,
0 + line_image.height)), line_image,
line_coords))
word_id = '%s_word%04d' % (line.id, word_no)
word = WordType(id=word_id, Coords=CoordsType(word_points))
line.add_Word(word)
word.add_TextEquiv(
TextEquivType(Unicode=word_str,
conf=wordsconf[word_no]))
if maxlevel == 'glyph':
for glyph_no, glyph_str in enumerate(word_str):
glyph_points = points_from_polygon(
coordinates_for_segment(
np.array(
polygon_from_bbox(
word_r_list[word_no][glyph_no] /
scale, 0,
word_r_list[word_no][glyph_no + 1]
/ scale, 0 + line_image.height)),
line_image, line_coords))
glyph_id = '%s_glyph%04d' % (word.id, glyph_no)
glyph = GlyphType(id=glyph_id,
Coords=CoordsType(glyph_points))
word.add_Glyph(glyph)
glyph.add_TextEquiv(
TextEquivType(
Unicode=glyph_str,
conf=word_conf_list[word_no][glyph_no]))
return edits, lengs
def process(self):
"""Performs word segmentation with Tesseract on the workspace.
Open and deserialize PAGE input files and their respective images,
then iterate over the element hierarchy down to the textline level,
and remove any existing Word elements (unless ``overwrite_words``
is False).
Set up Tesseract to detect words, and add each one to the line
at the detected coordinates.
Produce a new output file by serialising the resulting hierarchy.
"""
assert_file_grp_cardinality(self.input_file_grp, 1)
assert_file_grp_cardinality(self.output_file_grp, 1)
overwrite_words = self.parameter['overwrite_words']
with PyTessBaseAPI(
psm=PSM.SINGLE_LINE,
path=TESSDATA_PREFIX
) as tessapi:
for (n, input_file) in enumerate(self.input_files):
page_id = input_file.pageId or input_file.ID
LOG.info("INPUT FILE %i / %s", n, page_id)
pcgts = page_from_file(self.workspace.download_file(input_file))
page = pcgts.get_Page()
# add metadata about this operation and its runtime parameters:
metadata = pcgts.get_Metadata() # ensured by from_file()
metadata.add_MetadataItem(
MetadataItemType(type_="processingStep",
name=self.ocrd_tool['steps'][0],
value=TOOL,
Labels=[LabelsType(
externalModel="ocrd-tool",
externalId="parameters",
Label=[LabelType(type_=name,
value=self.parameter[name])
for name in self.parameter.keys()])]))
page_image, page_coords, page_image_info = self.workspace.image_from_page(
page, page_id)
if self.parameter['dpi'] > 0:
dpi = self.parameter['dpi']
LOG.info("Page '%s' images will use %d DPI from parameter override", page_id, dpi)
elif page_image_info.resolution != 1:
dpi = page_image_info.resolution
if page_image_info.resolutionUnit == 'cm':
dpi = round(dpi * 2.54)
LOG.info("Page '%s' images will use %d DPI from image meta-data", page_id, dpi)
else:
dpi = 0
LOG.info("Page '%s' images will use DPI estimated from segmentation", page_id)
if dpi:
tessapi.SetVariable('user_defined_dpi', str(dpi))
for region in page.get_TextRegion():
region_image, region_coords = self.workspace.image_from_segment(
region, page_image, page_coords)
for line in region.get_TextLine():
if line.get_Word():
if overwrite_words:
LOG.info('removing existing Words in line "%s"', line.id)
line.set_Word([])
else:
LOG.warning('keeping existing Words in line "%s"', line.id)
LOG.debug("Detecting words in line '%s'", line.id)
line_image, line_coords = self.workspace.image_from_segment(
line, region_image, region_coords)
tessapi.SetImage(line_image)
for word_no, component in enumerate(tessapi.GetComponentImages(RIL.WORD, True, raw_image=True)):
word_id = '%s_word%04d' % (line.id, word_no)
word_polygon = polygon_from_xywh(component[1])
word_polygon = coordinates_for_segment(word_polygon, line_image, line_coords)
word_points = points_from_polygon(word_polygon)
line.add_Word(WordType(
id=word_id, Coords=CoordsType(word_points)))
file_id = make_file_id(input_file, self.output_file_grp)
pcgts.set_pcGtsId(file_id)
self.workspace.add_file(
ID=file_id,
file_grp=self.output_file_grp,
pageId=input_file.pageId,
mimetype=MIMETYPE_PAGE,
local_filename=os.path.join(self.output_file_grp,
file_id + '.xml'),
content=to_xml(pcgts))
