fix: Improve OCR results, stricten criteria before dropping bitmap areas (#719)
fix: Properly care for all bitmap elements in OCR Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
@@ -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(
|
||||
|
||||
Reference in New Issue
Block a user