qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-10-26 23:34:13 +01:00
Code Issues Projects Releases Wiki Activity

find_number_of_columns_in_document: improve splitter rule

Browse source 
extend horizontal separators to full img width if they do not overlap
any other regions

(only as regards to returned `splitter_y` result,
 but without changing returned separators mask)
This commit is contained in:
Robert Sachunsky 2025-10-20 13:36:10 +02:00
parent 542d38ab43
commit 5a0e4c3b0f
1 changed files with 11 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

11
src/eynollah/utils/__init__.py
View file

@ -1378,6 +1378,8 @@ def return_points_with_boundies(peaks_neg_fin, first_point, last_point):
return peaks_neg_tot return peaks_neg_tot
def find_number_of_columns_in_document(region_pre_p, num_col_classifier, tables, label_seps, contours_h=None): def find_number_of_columns_in_document(region_pre_p, num_col_classifier, tables, label_seps, contours_h=None):
ncomps, ccomps = cv2.connectedComponents(region_pre_p.astype(np.uint8))
separators_closeup = 1 * (region_pre_p == label_seps) separators_closeup = 1 * (region_pre_p == label_seps)
separators_closeup[0:110] = 0 separators_closeup[0:110] = 0
separators_closeup[-150:] = 0 separators_closeup[-150:] = 0
@ -1398,10 +1400,19 @@ def find_number_of_columns_in_document(region_pre_p, num_col_classifier, tables,
min_xe = cnt[:, 0, 0].min() min_xe = cnt[:, 0, 0].min()
max_ye = cnt[:, 0, 1].max() max_ye = cnt[:, 0, 1].max()
min_ye = cnt[:, 0, 1].min() min_ye = cnt[:, 0, 1].min()
med_ye = int(np.median(cnt[:, 0, 1]))
dist_xe = max_xe - min_xe dist_xe = max_xe - min_xe
dist_ye = max_ye - min_ye dist_ye = max_ye - min_ye
if dist_ye <= 50 and dist_xe >= 3 * dist_ye: if dist_ye <= 50 and dist_xe >= 3 * dist_ye:
cnts_hor_e.append(cnt) cnts_hor_e.append(cnt)
labels = np.setdiff1d(np.unique(ccomps[med_ye]), [0])
if len(labels) == 1:
# mid line does not intersect with any other region
# so add it as extra splitter line
cnts_hor_e.append(np.array([[[0, med_ye]],
[[ccomps.shape[1], med_ye]],
[[ccomps.shape[1], med_ye + 1]],
[[0, med_ye + 1]]]))
# delete horizontal contours (leaving only the edges) # delete horizontal contours (leaving only the edges)
separators_closeup_n_binary = cv2.fillPoly(separators_closeup_n_binary, pts=cnts_hor_e, color=0) separators_closeup_n_binary = cv2.fillPoly(separators_closeup_n_binary, pts=cnts_hor_e, color=0)