NeoAnd/Docling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: Improve OCR results, stricten criteria before dropping bitmap areas (#719)

Browse Source 
fix: Properly care for all bitmap elements in OCR

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer
2025-01-10 10:38:49 +01:00
committed by GitHub
parent 9a6b5c8c8d
commit 5a060f237d
5 changed files with 19 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docling/backend/docling_parse_backend.py
View File

@@ -132,7 +132,7 @@ class DoclingParsePageBackend(PdfPageBackend):
return cells
def get_bitmap_rects(self, scale: float = 1) -> Iterable[BoundingBox]:
AREA_THRESHOLD = 32 * 32
AREA_THRESHOLD = 0 # 32 * 32
for i in range(len(self._dpage["images"])):
bitmap = self._dpage["images"][i]

2
docling/backend/docling_parse_v2_backend.py
View File

@@ -140,7 +140,7 @@ class DoclingParseV2PageBackend(PdfPageBackend):
return cells
def get_bitmap_rects(self, scale: float = 1) -> Iterable[BoundingBox]:
AREA_THRESHOLD = 32 * 32
AREA_THRESHOLD = 0 # 32 * 32
images = self._dpage["sanitized"]["images"]["data"]
images_header = self._dpage["sanitized"]["images"]["header"]

2
docling/backend/pypdfium2_backend.py
View File

@@ -39,7 +39,7 @@ class PyPdfiumPageBackend(PdfPageBackend):
return self.valid
def get_bitmap_rects(self, scale: float = 1) -> Iterable[BoundingBox]:
AREA_THRESHOLD = 32 * 32
AREA_THRESHOLD = 0 # 32 * 32
for obj in self._ppage.get_objects(filter=[pdfium_c.FPDF_PAGEOBJ_IMAGE]):
pos = obj.get_pos()
cropbox = BoundingBox.from_tuple(