mirror of
https://github.com/DS4SD/docling.git
synced 2025-12-10 13:48:13 +00:00
feat(ocr): auto-detect rotated pages in Tesseract (#1167)
* 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>
This commit is contained in:
Clément Doumouro
GitHub
@@ -2,6 +2,7 @@ import csv
|
||||
import io
|
||||
import logging
|
||||
import os
|
||||
import subprocess
|
||||
import tempfile
|
||||
from collections.abc import Iterable
|
||||
from pathlib import Path
|
||||
@@ -10,7 +11,7 @@ from typing import List, Optional, Tuple, Type
|
||||
|
||||
import pandas as pd
|
||||
from docling_core.types.doc import BoundingBox, CoordOrigin
|
||||
from docling_core.types.doc.page import BoundingRectangle, TextCell
|
||||
from docling_core.types.doc.page import TextCell
|
||||
|
||||
from docling.datamodel.base_models import Page
|
||||
from docling.datamodel.document import ConversionResult
|
||||
@@ -21,7 +22,11 @@ from docling.datamodel.pipeline_options import (
|
||||
)
|
||||
from docling.datamodel.settings import settings
|
||||
from docling.models.base_ocr_model import BaseOcrModel
|
||||
from docling.utils.ocr_utils import map_tesseract_script
|
||||
from docling.utils.ocr_utils import (
|
||||
map_tesseract_script,
|
||||
parse_tesseract_orientation,
|
||||
tesseract_box_to_bounding_rectangle,
|
||||
)
|
||||
from docling.utils.profiling import TimeRecorder
|
||||
|
||||
_log = logging.getLogger(__name__)
|
||||
@@ -49,6 +54,7 @@ class TesseractOcrCliModel(BaseOcrModel):
|
||||
self._version: Optional[str] = None
|
||||
self._tesseract_languages: Optional[List[str]] = None
|
||||
self._script_prefix: Optional[str] = None
|
||||
self._is_auto: bool = "auto" in self.options.lang
|
||||
|
||||
if self.enabled:
|
||||
try:
|
||||
@@ -93,14 +99,13 @@ class TesseractOcrCliModel(BaseOcrModel):
|
||||
|
||||
return name, version
|
||||
|
||||
def _run_tesseract(self, ifilename: str):
|
||||
def _run_tesseract(self, ifilename: str, osd: pd.DataFrame):
|
||||
r"""
|
||||
Run tesseract CLI
|
||||
"""
|
||||
cmd = [self.options.tesseract_cmd]
|
||||
|
||||
if "auto" in self.options.lang:
|
||||
lang = self._detect_language(ifilename)
|
||||
if self._is_auto:
|
||||
lang = self._parse_language(osd)
|
||||
if lang is not None:
|
||||
cmd.append("-l")
|
||||
cmd.append(lang)
|
||||
@@ -115,13 +120,12 @@ class TesseractOcrCliModel(BaseOcrModel):
|
||||
cmd += [ifilename, "stdout", "tsv"]
|
||||
_log.info("command: {}".format(" ".join(cmd)))
|
||||
|
||||
proc = Popen(cmd, stdout=PIPE, stderr=DEVNULL)
|
||||
output, _ = proc.communicate()
|
||||
output = subprocess.run(cmd, stdout=PIPE, stderr=DEVNULL, check=True)
|
||||
|
||||
# _log.info(output)
|
||||
|
||||
# Decode the byte string to a regular string
|
||||
decoded_data = output.decode("utf-8")
|
||||
decoded_data = output.stdout.decode("utf-8")
|
||||
# _log.info(decoded_data)
|
||||
|
||||
# Read the TSV file generated by Tesseract
|
||||
@@ -139,22 +143,24 @@ class TesseractOcrCliModel(BaseOcrModel):
|
||||
|
||||
return df_filtered
|
||||
|
||||
def _detect_language(self, ifilename: str):
|
||||
def _perform_osd(self, ifilename: str) -> pd.DataFrame:
|
||||
r"""
|
||||
Run tesseract in PSM 0 mode to detect the language
|
||||
"""
|
||||
assert self._tesseract_languages is not None
|
||||
|
||||
cmd = [self.options.tesseract_cmd]
|
||||
cmd.extend(["--psm", "0", "-l", "osd", ifilename, "stdout"])
|
||||
_log.info("command: {}".format(" ".join(cmd)))
|
||||
proc = Popen(cmd, stdout=PIPE, stderr=DEVNULL)
|
||||
output, _ = proc.communicate()
|
||||
decoded_data = output.decode("utf-8")
|
||||
output = subprocess.run(cmd, capture_output=True, check=True)
|
||||
decoded_data = output.stdout.decode("utf-8")
|
||||
df_detected = pd.read_csv(
|
||||
io.StringIO(decoded_data), sep=":", header=None, names=["key", "value"]
|
||||
)
|
||||
scripts = df_detected.loc[df_detected["key"] == "Script"].value.tolist()
|
||||
return df_detected
|
||||
|
||||
def _parse_language(self, df_osd: pd.DataFrame) -> Optional[str]:
|
||||
assert self._tesseract_languages is not None
|
||||
scripts = df_osd.loc[df_osd["key"] == "Script"].value.tolist()
|
||||
if len(scripts) == 0:
|
||||
_log.warning("Tesseract cannot detect the script of the page")
|
||||
return None
|
||||
@@ -182,9 +188,8 @@ class TesseractOcrCliModel(BaseOcrModel):
|
||||
cmd = [self.options.tesseract_cmd]
|
||||
cmd.append("--list-langs")
|
||||
_log.info("command: {}".format(" ".join(cmd)))
|
||||
proc = Popen(cmd, stdout=PIPE, stderr=DEVNULL)
|
||||
output, _ = proc.communicate()
|
||||
decoded_data = output.decode("utf-8")
|
||||
output = subprocess.run(cmd, stdout=PIPE, stderr=DEVNULL, check=True)
|
||||
decoded_data = output.stdout.decode("utf-8")
|
||||
df_list = pd.read_csv(io.StringIO(decoded_data), header=None)
|
||||
self._tesseract_languages = df_list[0].tolist()[1:]
|
||||
|
||||
@@ -203,7 +208,7 @@ class TesseractOcrCliModel(BaseOcrModel):
|
||||
yield from page_batch
|
||||
return
|
||||
|
||||
for page in page_batch:
|
||||
for page_i, page in enumerate(page_batch):
|
||||
assert page._backend is not None
|
||||
if not page._backend.is_valid():
|
||||
yield page
|
||||
@@ -212,7 +217,7 @@ class TesseractOcrCliModel(BaseOcrModel):
|
||||
ocr_rects = self.get_ocr_rects(page)
|
||||
|
||||
all_ocr_cells = []
|
||||
for ocr_rect in ocr_rects:
|
||||
for ocr_rect_i, ocr_rect in enumerate(ocr_rects):
|
||||
# Skip zero area boxes
|
||||
if ocr_rect.area() == 0:
|
||||
continue
|
||||
@@ -225,8 +230,42 @@ class TesseractOcrCliModel(BaseOcrModel):
|
||||
) as image_file:
|
||||
fname = image_file.name
|
||||
high_res_image.save(image_file)
|
||||
|
||||
df_result = self._run_tesseract(fname)
|
||||
doc_orientation = 0
|
||||
try:
|
||||
df_osd = self._perform_osd(fname)
|
||||
doc_orientation = _parse_orientation(df_osd)
|
||||
except subprocess.CalledProcessError as exc:
|
||||
_log.error(
|
||||
"OSD failed (doc %s, page: %s, "
|
||||
"OCR rectangle: %s, processed image file %s):\n %s",
|
||||
conv_res.input.file,
|
||||
page_i,
|
||||
ocr_rect_i,
|
||||
image_file,
|
||||
exc.stderr,
|
||||
)
|
||||
# Skipping if OSD fail when in auto mode, otherwise proceed
|
||||
# to OCR in the hope OCR will succeed while OSD failed
|
||||
if self._is_auto:
|
||||
continue
|
||||
if doc_orientation != 0:
|
||||
high_res_image = high_res_image.rotate(
|
||||
-doc_orientation, expand=True
|
||||
)
|
||||
high_res_image.save(fname)
|
||||
try:
|
||||
df_result = self._run_tesseract(fname, df_osd)
|
||||
except subprocess.CalledProcessError as exc:
|
||||
_log.error(
|
||||
"tesseract OCR failed (doc %s, page: %s, "
|
||||
"OCR rectangle: %s, processed image file %s):\n %s",
|
||||
conv_res.input.file,
|
||||
page_i,
|
||||
ocr_rect_i,
|
||||
image_file,
|
||||
exc.stderr,
|
||||
)
|
||||
continue
|
||||
finally:
|
||||
if os.path.exists(fname):
|
||||
os.remove(fname)
|
||||
@@ -238,31 +277,30 @@ class TesseractOcrCliModel(BaseOcrModel):
|
||||
text = row["text"]
|
||||
conf = row["conf"]
|
||||
|
||||
l = float(row["left"]) # noqa: E741
|
||||
b = float(row["top"])
|
||||
w = float(row["width"])
|
||||
h = float(row["height"])
|
||||
|
||||
t = b + h
|
||||
r = l + w
|
||||
|
||||
left, top = float(row["left"]), float(row["top"])
|
||||
right = left + float(row["width"])
|
||||
bottom = top + row["height"]
|
||||
bbox = BoundingBox(
|
||||
l=left,
|
||||
t=top,
|
||||
r=right,
|
||||
b=bottom,
|
||||
coord_origin=CoordOrigin.TOPLEFT,
|
||||
)
|
||||
rect = tesseract_box_to_bounding_rectangle(
|
||||
bbox,
|
||||
original_offset=ocr_rect,
|
||||
scale=self.scale,
|
||||
orientation=doc_orientation,
|
||||
im_size=high_res_image.size,
|
||||
)
|
||||
cell = TextCell(
|
||||
index=ix,
|
||||
text=str(text),
|
||||
orig=str(text),
|
||||
from_ocr=True,
|
||||
confidence=conf / 100.0,
|
||||
rect=BoundingRectangle.from_bounding_box(
|
||||
BoundingBox.from_tuple(
|
||||
coord=(
|
||||
(l / self.scale) + ocr_rect.l,
|
||||
(b / self.scale) + ocr_rect.t,
|
||||
(r / self.scale) + ocr_rect.l,
|
||||
(t / self.scale) + ocr_rect.t,
|
||||
),
|
||||
origin=CoordOrigin.TOPLEFT,
|
||||
)
|
||||
),
|
||||
rect=rect,
|
||||
)
|
||||
all_ocr_cells.append(cell)
|
||||
|
||||
@@ -278,3 +316,9 @@ class TesseractOcrCliModel(BaseOcrModel):
|
||||
@classmethod
|
||||
def get_options_type(cls) -> Type[OcrOptions]:
|
||||
return TesseractCliOcrOptions
|
||||
|
||||
|
||||
def _parse_orientation(df_osd: pd.DataFrame) -> int:
|
||||
orientations = df_osd.loc[df_osd["key"] == "Orientation in degrees"].value.tolist()
|
||||
orientation = parse_tesseract_orientation(orientations[0].strip())
|
||||
return orientation
|
||||
|
||||
@@ -1,12 +1,11 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from collections.abc import Iterable
|
||||
from pathlib import Path
|
||||
from typing import Optional, Type
|
||||
from typing import Iterable, Optional, Type
|
||||
|
||||
from docling_core.types.doc import BoundingBox, CoordOrigin
|
||||
from docling_core.types.doc.page import BoundingRectangle, TextCell
|
||||
from docling_core.types.doc.page import TextCell
|
||||
|
||||
from docling.datamodel.base_models import Page
|
||||
from docling.datamodel.document import ConversionResult
|
||||
@@ -17,7 +16,11 @@ from docling.datamodel.pipeline_options import (
|
||||
)
|
||||
from docling.datamodel.settings import settings
|
||||
from docling.models.base_ocr_model import BaseOcrModel
|
||||
from docling.utils.ocr_utils import map_tesseract_script
|
||||
from docling.utils.ocr_utils import (
|
||||
map_tesseract_script,
|
||||
parse_tesseract_orientation,
|
||||
tesseract_box_to_bounding_rectangle,
|
||||
)
|
||||
from docling.utils.profiling import TimeRecorder
|
||||
|
||||
_log = logging.getLogger(__name__)
|
||||
@@ -38,7 +41,7 @@ class TesseractOcrModel(BaseOcrModel):
|
||||
accelerator_options=accelerator_options,
|
||||
)
|
||||
self.options: TesseractOcrOptions
|
||||
|
||||
self._is_auto: bool = "auto" in self.options.lang
|
||||
self.scale = 3 # multiplier for 72 dpi == 216 dpi.
|
||||
self.reader = None
|
||||
self.script_readers: dict[str, tesserocr.PyTessBaseAPI] = {}
|
||||
@@ -95,13 +98,13 @@ class TesseractOcrModel(BaseOcrModel):
|
||||
|
||||
if lang == "auto":
|
||||
self.reader = tesserocr.PyTessBaseAPI(**tesserocr_kwargs)
|
||||
self.osd_reader = tesserocr.PyTessBaseAPI(
|
||||
**{"lang": "osd", "psm": tesserocr.PSM.OSD_ONLY} | tesserocr_kwargs
|
||||
)
|
||||
else:
|
||||
self.reader = tesserocr.PyTessBaseAPI(
|
||||
**{"lang": lang} | tesserocr_kwargs,
|
||||
)
|
||||
self.osd_reader = tesserocr.PyTessBaseAPI(
|
||||
**{"lang": "osd", "psm": tesserocr.PSM.OSD_ONLY} | tesserocr_kwargs
|
||||
)
|
||||
self.reader_RIL = tesserocr.RIL
|
||||
|
||||
def __del__(self):
|
||||
@@ -118,19 +121,20 @@ class TesseractOcrModel(BaseOcrModel):
|
||||
yield from page_batch
|
||||
return
|
||||
|
||||
for page in page_batch:
|
||||
for page_i, page in enumerate(page_batch):
|
||||
assert page._backend is not None
|
||||
if not page._backend.is_valid():
|
||||
yield page
|
||||
else:
|
||||
with TimeRecorder(conv_res, "ocr"):
|
||||
assert self.reader is not None
|
||||
assert self.osd_reader is not None
|
||||
assert self._tesserocr_languages is not None
|
||||
|
||||
ocr_rects = self.get_ocr_rects(page)
|
||||
|
||||
all_ocr_cells = []
|
||||
for ocr_rect in ocr_rects:
|
||||
for ocr_rect_i, ocr_rect in enumerate(ocr_rects):
|
||||
# Skip zero area boxes
|
||||
if ocr_rect.area() == 0:
|
||||
continue
|
||||
@@ -139,16 +143,27 @@ class TesseractOcrModel(BaseOcrModel):
|
||||
)
|
||||
|
||||
local_reader = self.reader
|
||||
if "auto" in self.options.lang:
|
||||
assert self.osd_reader is not None
|
||||
|
||||
self.osd_reader.SetImage(high_res_image)
|
||||
osd = self.osd_reader.DetectOrientationScript()
|
||||
|
||||
# No text, probably
|
||||
if osd is None:
|
||||
self.osd_reader.SetImage(high_res_image)
|
||||
osd = self.osd_reader.DetectOrientationScript()
|
||||
# No text, or Orientation and Script detection failure
|
||||
if osd is None:
|
||||
_log.error(
|
||||
"OSD failed for doc (doc %s, page: %s, "
|
||||
"OCR rectangle: %s)",
|
||||
conv_res.input.file,
|
||||
page_i,
|
||||
ocr_rect_i,
|
||||
)
|
||||
# Skipping if OSD fail when in auto mode, otherwise proceed
|
||||
# to OCR in the hope OCR will succeed while OSD failed
|
||||
if self._is_auto:
|
||||
continue
|
||||
|
||||
doc_orientation = parse_tesseract_orientation(osd["orient_deg"])
|
||||
if doc_orientation != 0:
|
||||
high_res_image = high_res_image.rotate(
|
||||
-doc_orientation, expand=True
|
||||
)
|
||||
if self._is_auto:
|
||||
script = osd["script_name"]
|
||||
script = map_tesseract_script(script)
|
||||
lang = f"{self.script_prefix}{script}"
|
||||
@@ -188,11 +203,23 @@ class TesseractOcrModel(BaseOcrModel):
|
||||
# Extract text within the bounding box
|
||||
text = local_reader.GetUTF8Text().strip()
|
||||
confidence = local_reader.MeanTextConf()
|
||||
left = box["x"] / self.scale
|
||||
bottom = box["y"] / self.scale
|
||||
right = (box["x"] + box["w"]) / self.scale
|
||||
top = (box["y"] + box["h"]) / self.scale
|
||||
|
||||
left, top = box["x"], box["y"]
|
||||
right = left + box["w"]
|
||||
bottom = top + box["h"]
|
||||
bbox = BoundingBox(
|
||||
l=left,
|
||||
t=top,
|
||||
r=right,
|
||||
b=bottom,
|
||||
coord_origin=CoordOrigin.TOPLEFT,
|
||||
)
|
||||
rect = tesseract_box_to_bounding_rectangle(
|
||||
bbox,
|
||||
original_offset=ocr_rect,
|
||||
scale=self.scale,
|
||||
orientation=doc_orientation,
|
||||
im_size=high_res_image.size,
|
||||
)
|
||||
cells.append(
|
||||
TextCell(
|
||||
index=ix,
|
||||
@@ -200,12 +227,7 @@ class TesseractOcrModel(BaseOcrModel):
|
||||
orig=text,
|
||||
from_ocr=True,
|
||||
confidence=confidence,
|
||||
rect=BoundingRectangle.from_bounding_box(
|
||||
BoundingBox.from_tuple(
|
||||
coord=(left, top, right, bottom),
|
||||
origin=CoordOrigin.TOPLEFT,
|
||||
),
|
||||
),
|
||||
rect=rect,
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
@@ -1,3 +1,11 @@
|
||||
from typing import Optional, Tuple
|
||||
|
||||
from docling_core.types.doc import BoundingBox, CoordOrigin
|
||||
from docling_core.types.doc.page import BoundingRectangle
|
||||
|
||||
from docling.utils.orientation import CLIPPED_ORIENTATIONS, rotate_bounding_box
|
||||
|
||||
|
||||
def map_tesseract_script(script: str) -> str:
|
||||
r""" """
|
||||
if script == "Katakana" or script == "Hiragana":
|
||||
@@ -7,3 +15,55 @@ def map_tesseract_script(script: str) -> str:
|
||||
elif script == "Korean":
|
||||
script = "Hangul"
|
||||
return script
|
||||
|
||||
|
||||
def parse_tesseract_orientation(orientation: str) -> int:
|
||||
# Tesseract orientation is [0, 90, 180, 270] clockwise, bounding rectangle angles
|
||||
# are [0, 360[ counterclockwise
|
||||
parsed = int(orientation)
|
||||
if parsed not in CLIPPED_ORIENTATIONS:
|
||||
msg = (
|
||||
f"invalid tesseract document orientation {orientation}, "
|
||||
f"expected orientation: {sorted(CLIPPED_ORIENTATIONS)}"
|
||||
)
|
||||
raise ValueError(msg)
|
||||
parsed = -parsed
|
||||
parsed %= 360
|
||||
return parsed
|
||||
|
||||
|
||||
def tesseract_box_to_bounding_rectangle(
|
||||
bbox: BoundingBox,
|
||||
*,
|
||||
original_offset: Optional[BoundingBox] = None,
|
||||
scale: float,
|
||||
orientation: int,
|
||||
im_size: Tuple[int, int],
|
||||
) -> BoundingRectangle:
|
||||
# box is in the top, left, height, width format, top left coordinates
|
||||
rect = rotate_bounding_box(bbox, angle=-orientation, im_size=im_size)
|
||||
rect = BoundingRectangle(
|
||||
r_x0=rect.r_x0 / scale,
|
||||
r_y0=rect.r_y0 / scale,
|
||||
r_x1=rect.r_x1 / scale,
|
||||
r_y1=rect.r_y1 / scale,
|
||||
r_x2=rect.r_x2 / scale,
|
||||
r_y2=rect.r_y2 / scale,
|
||||
r_x3=rect.r_x3 / scale,
|
||||
r_y3=rect.r_y3 / scale,
|
||||
coord_origin=CoordOrigin.TOPLEFT,
|
||||
)
|
||||
if original_offset is not None:
|
||||
if original_offset.coord_origin is not CoordOrigin.TOPLEFT:
|
||||
msg = f"expected coordinate origin to be {CoordOrigin.TOPLEFT.value}"
|
||||
raise ValueError(msg)
|
||||
if original_offset is not None:
|
||||
rect.r_x0 += original_offset.l
|
||||
rect.r_x1 += original_offset.l
|
||||
rect.r_x2 += original_offset.l
|
||||
rect.r_x3 += original_offset.l
|
||||
rect.r_y0 += original_offset.t
|
||||
rect.r_y1 += original_offset.t
|
||||
rect.r_y2 += original_offset.t
|
||||
rect.r_y3 += original_offset.t
|
||||
return rect
|
||||
|
||||
71
docling/utils/orientation.py
Normal file
71
docling/utils/orientation.py
Normal file
@@ -0,0 +1,71 @@
|
||||
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,
|
||||
)
|
||||
Reference in New Issue
Block a user