qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-12-01 08:44:13 +01:00
Code Issues Projects Releases Wiki Activity

return_boxes_of_images_by_order_of_reading_new: always erode

Browse source 
when passing the text region mask, do not apply erosion only
if there are more than 2 columns, but iff `not erosion_hurts`
(consistent with `find_num_col`'s expectations and making
 it as easy to find the column gaps on 1 and 2-column pages
 as on multi-column pages)
This commit is contained in:
Robert Sachunsky 2025-11-28 18:23:59 +01:00
parent 5a3de3b42d
commit adcea47bc0
1 changed files with 8 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

21
src/eynollah/eynollah.py
View file

@ -2356,7 +2356,6 @@ class Eynollah:
img_only_regions_with_sep = (prediction_regions_org_y == 1).astype(np.uint8)
try:
img_only_regions = cv2.erode(img_only_regions_with_sep[:,:], KERNEL, iterations=20)
_, _ = find_num_col(img_only_regions, num_col_classifier, self.tables, multiplier=6.0)
img = resize_image(img_org, int(img_org.shape[0]), int(img_org.shape[1]*(1.2 if is_image_enhanced else 1)))
prediction_regions_org = self.do_prediction(True, img, self.models["region"])
@ -3138,7 +3137,7 @@ class Eynollah:
#print(time.time()-t_0_box,'time box in 2')
self.logger.info("num_col_classifier: %s", num_col_classifier)
if num_col_classifier >= 3:
if not erosion_hurts:
if np.abs(slope_deskew) < SLOPE_THRESHOLD:
regions_without_separators = regions_without_separators.astype(np.uint8)
regions_without_separators = cv2.erode(regions_without_separators[:, :], KERNEL, iterations=6)
@ -3289,21 +3288,16 @@ class Eynollah:
if np.abs(slope_deskew) < SLOPE_THRESHOLD:
num_col, _, matrix_of_seps_ch, splitter_y_new, _ = find_number_of_columns_in_document(
text_regions_p, num_col_classifier, self.tables, label_seps)
if np.abs(slope_deskew) >= SLOPE_THRESHOLD:
num_col_d, _, matrix_of_seps_ch_d, splitter_y_new_d, _ = find_number_of_columns_in_document(
text_regions_p_d, num_col_classifier, self.tables, label_seps)
if num_col_classifier>=3:
if np.abs(slope_deskew) < SLOPE_THRESHOLD:
if not erosion_hurts:
regions_without_separators = regions_without_separators.astype(np.uint8)
regions_without_separators = cv2.erode(regions_without_separators[:,:], KERNEL, iterations=6)
if np.abs(slope_deskew) >= SLOPE_THRESHOLD:
else:
num_col_d, _, matrix_of_seps_ch_d, splitter_y_new_d, _ = find_number_of_columns_in_document(
text_regions_p_d, num_col_classifier, self.tables, label_seps)
if not erosion_hurts:
regions_without_separators_d = regions_without_separators_d.astype(np.uint8)
regions_without_separators_d = cv2.erode(regions_without_separators_d[:,:], KERNEL, iterations=6)
else:
pass
if np.abs(slope_deskew) < SLOPE_THRESHOLD:
boxes, peaks_neg_tot_tables = return_boxes_of_images_by_order_of_reading_new(
@ -4149,6 +4143,7 @@ class Eynollah:
self.run_enhancement(self.light_version)
self.logger.info(f"Image: {self.image.shape[1]}x{self.image.shape[0]}, "
f"scale {self.scale_x:.1f}x{self.scale_y:.1f}, "
f"{self.dpi} DPI, {num_col_classifier} columns")
if is_image_enhanced:
self.logger.info("Enhancement applied")
@ -4682,7 +4677,7 @@ class Eynollah:
_, _, matrix_of_seps_ch_d, splitter_y_new_d, _ = find_number_of_columns_in_document(
text_regions_p_d, num_col_classifier, self.tables, label_seps)
if num_col_classifier >= 3:
if not erosion_hurts:
if np.abs(slope_deskew) < SLOPE_THRESHOLD:
regions_without_separators = regions_without_separators.astype(np.uint8)
regions_without_separators = cv2.erode(regions_without_separators[:, :], KERNEL, iterations=6)