qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2026-04-30 19:22:03 +02:00
Code Issues Projects Releases Wiki Activity

return_boxes_...order_of_reading...: avoid negative slices…

Browse source 
fix rare bug when horizontal separators are detected
by the very top (of a major vertical part of the page),
causing box intervals to become negative
This commit is contained in:
Robert Sachunsky 2026-04-27 00:42:31 +02:00
parent 6a92f0d49c
commit 2641171fb1
2 changed files with 17 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/eynollah/eynollah.py
View file

@ -1175,7 +1175,7 @@ class Eynollah:
boxes,
textline_mask_tot
):
assert np.any(textline_mask_tot)
self.logger.debug("enter do_order_of_regions")
contours_only_text_parent = ensure_array(contours_only_text_parent)
contours_only_text_parent_h = ensure_array(contours_only_text_parent_h)

21
src/eynollah/utils/__init__.py
View file

@ -1056,8 +1056,11 @@ def order_of_regions(textline_mask, contours_main, contours_head, contours_drop,
* the array of contour indexes for the respective type
(i.e. into contours_main or contours_head or contours_drop)
"""
##plt.imshow(textline_mask)
##plt.show()
total = len(contours_main) + len(contours_head) + len(contours_drop)
assert total == 0 or np.any(textline_mask)
# ax1 = plt.subplot(2, 1, 1, title="order_of_regions textline_mask")
# plt.imshow(textline_mask, aspect='auto')
y = textline_mask.sum(axis=1) # horizontal projection profile
y_padded = np.zeros(len(y) + 40)
y_padded[20 : len(y) + 20] = y
@ -1066,14 +1069,16 @@ def order_of_regions(textline_mask, contours_main, contours_head, contours_drop,
#z = gaussian_filter1d(y_padded, sigma_gaus)
#peaks, _ = find_peaks(z, height=0)
#peaks = peaks - 20
##plt.plot(z)
##plt.show()
# ax2 = plt.subplot(2, 1, 2, title="smoothed horizontal projection", sharex=ax1)
# plt.plot(y)
zneg_rev = np.max(y_padded) - y_padded
zneg = np.zeros(len(zneg_rev) + 40)
zneg[20 : len(zneg_rev) + 20] = zneg_rev
zneg = gaussian_filter1d(zneg, sigma_gaus)
peaks_neg, _ = find_peaks(zneg, height=0)
# plt.vlines(peaks_neg - 40, 0, None, label="peaks")
# plt.show()
peaks_neg = peaks_neg - 20 - 20
peaks_neg_new = np.array([0] +
@ -1091,7 +1096,6 @@ def order_of_regions(textline_mask, contours_main, contours_head, contours_drop,
# assert not len(cy_head) or np.min(peaks_neg_new) <= np.min(cy_head) and np.max(cy_head) <= np.max(peaks_neg_new)
# assert not len(cy_drop) or np.min(peaks_neg_new) <= np.min(cy_drop) and np.max(cy_drop) <= np.max(peaks_neg_new)
total = len(contours_main) + len(contours_head) + len(contours_drop)
slice_main = slice(0, len(contours_main))
slice_head = slice(len(contours_main),
len(contours_main) + len(contours_head))
@ -1778,6 +1782,13 @@ def return_boxes_of_images_by_order_of_reading_new(
y_max_hor_some = np.append(y_max_hor_some, [label_top, label_bot + 2])
cy_hor_some = np.append(cy_hor_some, [label_top - 1, label_bot + 1])
# ensure no seps are out of bounds
x_min_hor_some = np.maximum(0, np.minimum(width_tot, x_min_hor_some))
x_max_hor_some = np.maximum(0, np.minimum(width_tot, x_max_hor_some))
y_min_hor_some = np.maximum(0, np.minimum(height_tot, y_min_hor_some))
y_max_hor_some = np.maximum(0, np.minimum(height_tot, y_max_hor_some))
cy_hor_some = np.maximum(0, np.minimum(height_tot, cy_hor_some))
if right2left_readingorder:
x_max_hor_some = width_tot - x_min_hor_some
x_min_hor_some = width_tot - x_max_hor_some