From e535a070c4a2c9ca64dcf284476697cd9852fa51 Mon Sep 17 00:00:00 2001 From: Clemens Neudecker <952378+cneud@users.noreply.github.com> Date: Thu, 20 Feb 2020 18:35:16 +0100 Subject: [PATCH] Update cli.py --- cli.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/cli.py b/cli.py index 87da500..aea75d7 100644 --- a/cli.py +++ b/cli.py @@ -173,7 +173,7 @@ 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 derive the correct coords for the web presentation image + # transform OCR coordinates using `scale_factor` to derive correct coordinates for the web presentation image points = [int(scale_factor * 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)]