Files
rapidocr/python
Mohammad Hijjawi cee004f994 fix(word_box): place word boxes correctly on 180-degree rotated lines (issue #328) (#747)
When the text classifier turns a crop by 180 degrees, recognition runs on
the rotated crop, but CalRecBoxes mapped the word boxes back as if the crop
had never been rotated. Every word/char box on an upside-down line therefore
landed on its mirror position: the first character got the box of the last.

Pass the classifier's rotation decision (same "180" label and cls_thresh
rule TextClassifier uses) to CalRecBoxes, and rotate the word boxes back
by 180 degrees within the crop before mapping them to the original image.
2026-10-25 08:17:53 +08:00
..
2026-02-01 14:36:32 +08:00