qurator-spk/ocrd_calamari
1
0
Fork 0
mirror of https://github.com/mikegerber/ocrd_calamari.git synced 2025-06-10 04:09:53 +02:00
Code Releases Activity

🐛 Start with TextEquiv index=1 to adhere to OCR-D PAGE conventions

Browse source 
https://ocr-d.github.io/page#multiple-textequivs
This commit is contained in:
Gerber, Mike 2020-02-03 17:40:45 +01:00
parent 909632493b
commit 0f9c94e7dc
1 changed files with 5 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

8
ocrd_calamari/recognize.py
View file

@ -142,10 +142,12 @@ class CalamariRecognize(Processor):
glyph = GlyphType(id='%s_glyph%04d' % (word.id, glyph_no), Coords=CoordsType(points))
chars = sorted(p.chars, key=lambda k: k.probability, reverse=True)
for index, char in enumerate(chars):
char_index = 1 # Must start with 1, see https://ocr-d.github.io/page#multiple-textequivs
for char in chars:
if char.char:
glyph.add_TextEquiv(TextEquivType(Unicode=char.char, index=index, conf=char.probability))
# XXX Note that omission probabilities are not normalized?!
glyph.add_TextEquiv(TextEquivType(Unicode=char.char, index=char_index, conf=char.probability))
char_index += 1
# XXX Note that omission probabilities are not normalized?!
word.add_Glyph(glyph)