def _process_words_in_line(self, line, maxlevel, result_it):
for word_no in range(
0, MAX_ELEMENTS
): # iterate until IsAtFinalElement(RIL.LINE, RIL.WORD)
if not result_it:
log.error("No iterator at '%s'", line.id)
break
if result_it.Empty(RIL.WORD):
log.debug("No word here")
break
word_id = '%s_word%04d' % (line.id, word_no)
log.debug("Recognizing text in word '%s'", word_id)
word_bbox = result_it.BoundingBox(RIL.WORD)
word = WordType(id=word_id,
Coords=CoordsType(points_from_x0y0x1y1(word_bbox)))
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=None if 'bold' not in word_attributes else
word_attributes['bold'],
italic=None if 'italic' not in word_attributes else
word_attributes['italic'],
underlined=None if 'underlined' not in word_attributes else
word_attributes['underlined'],
monospace=None if 'monospace' not in word_attributes else
word_attributes['monospace'],
serif=None if 'serif' not in word_attributes else
word_attributes['serif'])
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 maxlevel == 'word':
pass
else:
self._process_glyphs_in_word(word, result_it)
if result_it.IsAtFinalElement(RIL.TEXTLINE, RIL.WORD):
break
else:
result_it.Next(RIL.WORD)
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'))
def _process_glyphs_in_word(self, word, result_it):
for glyph_no in range(
0, MAX_ELEMENTS
): # iterate until IsAtFinalElement(RIL.WORD, RIL.SYMBOL)
if not result_it:
log.error("No iterator at '%s'", word.id)
break
if result_it.Empty(RIL.SYMBOL):
log.debug("No glyph here")
break
glyph_id = '%s_glyph%04d' % (word.id, glyph_no)
log.debug("Recognizing text in glyph '%s'", glyph_id)
# glyph_text = result_it.GetUTF8Text(RIL.SYMBOL) # equals first choice?
glyph_conf = result_it.Confidence(
RIL.SYMBOL) / 100 # equals first choice?
#log.debug('best glyph: "%s" [%f]', glyph_text, glyph_conf)
glyph_bbox = result_it.BoundingBox(RIL.SYMBOL)
glyph = GlyphType(id=glyph_id,
Coords=CoordsType(
points_from_x0y0x1y1(glyph_bbox)))
word.add_Glyph(glyph)
choice_it = result_it.GetChoiceIterator()
for (choice_no, choice) in enumerate(choice_it):
alternative_text = choice.GetUTF8Text()
alternative_conf = choice.Confidence() / 100
#log.debug('alternative glyph: "%s" [%f]', alternative_text, alternative_conf)
if (glyph_conf - alternative_conf > CHOICE_THRESHOLD_CONF
or choice_no > CHOICE_THRESHOLD_NUM):
break
# todo: consider SymbolIsSuperscript (TextStyle), SymbolIsDropcap (RelationType) etc
glyph.add_TextEquiv(
TextEquivType(index=choice_no,
Unicode=alternative_text,
conf=alternative_conf))
if result_it.IsAtFinalElement(RIL.WORD, RIL.SYMBOL):
break
else:
result_it.Next(RIL.SYMBOL)
def test_points_from_x0y0x1y1(self):
self.assertEqual(points_from_x0y0x1y1([100, 100, 200, 200]),
'100,100 200,100 200,200 100,200')
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])))
