qurator-spk/ocrd_calamari
1
0
Fork 0
mirror of https://github.com/mikegerber/ocrd_calamari.git synced 2025-06-09 03:39:55 +02:00
Code Releases Activity

🚧 Add future TODOs

Browse source
This commit is contained in:
Gerber, Mike 2020-02-03 17:37:19 +01:00
parent 3149e1d9e0
commit 909632493b
1 changed files with 2 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ocrd_calamari/recognize.py
View file

@ -116,6 +116,7 @@ class CalamariRecognize(Processor):
word_no = 0 word_no = 0
i = 0 i = 0
for word_text in uniseg.wordbreak.words(prediction.sentence): for word_text in uniseg.wordbreak.words(prediction.sentence):
# XXX Re-use word segmentation from dinglehopper, i.e. support private use characters
word_length = len(word_text) word_length = len(word_text)
do_not_include = all(unwanted(c) for c in word_text) do_not_include = all(unwanted(c) for c in word_text)
@ -126,6 +127,7 @@ class CalamariRecognize(Processor):
polygon = polygon_from_x0y0x1y1([word_start, 0, word_end, line_image.height]) polygon = polygon_from_x0y0x1y1([word_start, 0, word_end, line_image.height])
points = points_from_polygon(coordinates_for_segment(polygon, None, line_coords)) 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 = WordType(id='%s_word%04d' % (line.id, word_no), Coords=CoordsType(points))
word.add_TextEquiv(TextEquivType(Unicode=word_text)) word.add_TextEquiv(TextEquivType(Unicode=word_text))