feat: add coverage_threshold to skip OCR for small images (#161)

* feat: add coverage_threshold to skip OCR for small images

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* filter individual boxes

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* rename option

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

docling/datamodel/pipeline_options.py

@@ -22,6 +22,9 @@ class TableStructureOptions(BaseModel):
 
 class OcrOptions(BaseModel):
     kind: str
+    bitmap_area_threshold: float = (
+        0.05  # percentage of the area for a bitmap to processed with OCR
+    )
 
 
 class EasyOcrOptions(OcrOptions):

docling/models/base_ocr_model.py

@@ -69,7 +69,7 @@ class BaseOcrModel:
         coverage, ocr_rects = find_ocr_rects(page.size, bitmap_rects)
 
         # return full-page rectangle if sufficiently covered with bitmaps
-        if coverage > BITMAP_COVERAGE_TRESHOLD:
+        if coverage > max(BITMAP_COVERAGE_TRESHOLD, self.options.bitmap_area_threshold):
             return [
                 BoundingBox(
                     l=0,
@@ -81,6 +81,14 @@ class BaseOcrModel:
             ]
         # return individual rectangles if the bitmap coverage is smaller
         else:  # coverage <= BITMAP_COVERAGE_TRESHOLD:
+
+            # skip OCR if the bitmap area on the page is smaller than the options threshold
+            ocr_rects = [
+                rect
+                for rect in ocr_rects
+                if rect.area() / (page.size.width * page.size.height)
+                > self.options.bitmap_area_threshold
+            ]
             return ocr_rects
 
     # Filters OCR cells by dropping any OCR cell that intersects with an existing programmatic cell.