1
0
Fork 0
mirror of https://github.com/qurator-spk/neat.git synced 2025-06-11 04:39:54 +02:00
This commit is contained in:
cneud 2019-12-06 15:25:09 +01:00
parent d01d793928
commit 98e48dec38

View file

@ -172,7 +172,7 @@ def page2tsv(page_xml_file, tsv_out_file, image_url, ner_rest_endpoint, noproxy)
text = word.text
for coords in words.findall('.//{%s}Coords' % xmlns):
# transform the OCR coordinates by 0.5685 to derived the correct coords for the web presentation
# transform the OCR coordinates by 0.5685 to derive the correct coords for the web presentation image
points = [int(0.5685 * float(pos)) for p in coords.attrib['points'].split(' ') for pos in p.split(',')]
x_points = [points[i] for i in range(0, len(points), 2)]