45265bf8b1
* fix(ocr): tesseract support mis-oriented documents Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com> * fix(ocr): update missing test data Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com> * fix(ocr): rotate image to the natural orientation before layout prediction Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com> * fix(ocr): move bounding bow rotation util to orientation.py Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com> * fix(ocr): refactor rotation utilities Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com> * chore(ocr): revert layout updates Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com> * chore(ocr): update e2e OCR test data Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com> * fix(ocr): avoid to swallow tesseract errors causing orientation detection failures Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com> * chore(ocr): revert layout updates Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com> * chore(ocr): update e2e OCR test data * chore(ocr): proceed to OCR without rotation when OSD fails in `TesseractOcrCliModel` * chore(ocr): proceed to OCR without rotation when OSD fails in `TesseractOcrModel` * chore(ocr): default `TesseractOcrCliModel._is_auto` to `False` * fix(ocr): fix `TesseractOcrCliModel._is_auto` computation * chore(ocr): improve logging in case of OSD failure in `TesseractOcrCliModel` and `TesseractOcrModel` --------- Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>
72 lines
2.0 KiB
Python
72 lines
2.0 KiB
Python
from typing import Tuple
|
|
|
|
from docling_core.types.doc import BoundingBox, CoordOrigin
|
|
from docling_core.types.doc.page import BoundingRectangle
|
|
|
|
CLIPPED_ORIENTATIONS = [0, 90, 180, 270]
|
|
|
|
|
|
def rotate_bounding_box(
|
|
bbox: BoundingBox, angle: int, im_size: Tuple[int, int]
|
|
) -> BoundingRectangle:
|
|
# The box is left top width height in TOPLEFT coordinates
|
|
# Bounding rectangle start with r_0 at the bottom left whatever the
|
|
# coordinate system. Then other corners are found rotating counterclockwise
|
|
bbox = bbox.to_top_left_origin(im_size[1])
|
|
left, top, width, height = bbox.l, bbox.t, bbox.width, bbox.height
|
|
im_h, im_w = im_size
|
|
angle = angle % 360
|
|
if angle == 0:
|
|
r_x0 = left
|
|
r_y0 = top + height
|
|
r_x1 = r_x0 + width
|
|
r_y1 = r_y0
|
|
r_x2 = r_x0 + width
|
|
r_y2 = r_y0 - height
|
|
r_x3 = r_x0
|
|
r_y3 = r_y0 - height
|
|
elif angle == 90:
|
|
r_x0 = im_w - (top + height)
|
|
r_y0 = left
|
|
r_x1 = r_x0
|
|
r_y1 = r_y0 + width
|
|
r_x2 = r_x0 + height
|
|
r_y2 = r_y0 + width
|
|
r_x3 = r_x0
|
|
r_y3 = r_y0 + width
|
|
elif angle == 180:
|
|
r_x0 = im_h - left
|
|
r_y0 = im_w - (top + height)
|
|
r_x1 = r_x0 - width
|
|
r_y1 = r_y0
|
|
r_x2 = r_x0 - width
|
|
r_y2 = r_y0 + height
|
|
r_x3 = r_x0
|
|
r_y3 = r_y0 + height
|
|
elif angle == 270:
|
|
r_x0 = top + height
|
|
r_y0 = im_h - left
|
|
r_x1 = r_x0
|
|
r_y1 = r_y0 - width
|
|
r_x2 = r_x0 - height
|
|
r_y2 = r_y0 - width
|
|
r_x3 = r_x0 - height
|
|
r_y3 = r_y0
|
|
else:
|
|
msg = (
|
|
f"invalid orientation {angle}, expected values in:"
|
|
f" {sorted(CLIPPED_ORIENTATIONS)}"
|
|
)
|
|
raise ValueError(msg)
|
|
return BoundingRectangle(
|
|
r_x0=r_x0,
|
|
r_y0=r_y0,
|
|
r_x1=r_x1,
|
|
r_y1=r_y1,
|
|
r_x2=r_x2,
|
|
r_y2=r_y2,
|
|
r_x3=r_x3,
|
|
r_y3=r_y3,
|
|
coord_origin=CoordOrigin.TOPLEFT,
|
|
)
|