qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-06-08 11:49:55 +02:00
Code Issues Projects Releases Wiki Activity

modifications

Browse source
This commit is contained in:
vahid 2021-07-13 19:58:08 -04:00
parent 14c588e162
commit 0859d22f4c
1 changed files with 13 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

25
qurator/eynollah/eynollah.py
View file

@ -2275,19 +2275,20 @@ class Eynollah:
text_regions_p[:, :][regions_fully_np[:, :, 0] == 4] = 4 text_regions_p[:, :][regions_fully_np[:, :, 0] == 4] = 4
#plt.imshow(text_regions_p) #plt.imshow(text_regions_p)
#plt.show() #plt.show()
if not self.tables: ####if not self.tables:
if np.abs(slope_deskew) >= SLOPE_THRESHOLD: if np.abs(slope_deskew) >= SLOPE_THRESHOLD:
_, textline_mask_tot_d, text_regions_p_1_n, regions_fully_n = rotation_not_90_func_full_layout(image_page, textline_mask_tot, text_regions_p, regions_fully, slope_deskew) _, textline_mask_tot_d, text_regions_p_1_n, regions_fully_n = rotation_not_90_func_full_layout(image_page, textline_mask_tot, text_regions_p, regions_fully, slope_deskew)
text_regions_p_1_n = resize_image(text_regions_p_1_n, text_regions_p.shape[0], text_regions_p.shape[1]) text_regions_p_1_n = resize_image(text_regions_p_1_n, text_regions_p.shape[0], text_regions_p.shape[1])
textline_mask_tot_d = resize_image(textline_mask_tot_d, text_regions_p.shape[0], text_regions_p.shape[1]) textline_mask_tot_d = resize_image(textline_mask_tot_d, text_regions_p.shape[0], text_regions_p.shape[1])
regions_fully_n = resize_image(regions_fully_n, text_regions_p.shape[0], text_regions_p.shape[1]) regions_fully_n = resize_image(regions_fully_n, text_regions_p.shape[0], text_regions_p.shape[1])
if not self.tables:
regions_without_separators_d = (text_regions_p_1_n[:, :] == 1) * 1 regions_without_separators_d = (text_regions_p_1_n[:, :] == 1) * 1
else: else:
text_regions_p_1_n = None text_regions_p_1_n = None
textline_mask_tot_d = None textline_mask_tot_d = None
regions_without_separators_d = None regions_without_separators_d = None
if not self.tables:
regions_without_separators = (text_regions_p[:, :] == 1) * 1 regions_without_separators = (text_regions_p[:, :] == 1) * 1
K.clear_session() K.clear_session()
@ -2342,7 +2343,6 @@ class Eynollah:
if self.full_layout: if self.full_layout:
polygons_of_images, img_revised_tab, text_regions_p_1_n, textline_mask_tot_d, regions_without_separators_d, regions_fully, regions_without_separators, polygons_of_marginals, contours_tables = self.run_boxes_full_layout(image_page, textline_mask_tot, text_regions_p, slope_deskew, num_col_classifier, img_only_regions, table_prediction, erosion_hurts) polygons_of_images, img_revised_tab, text_regions_p_1_n, textline_mask_tot_d, regions_without_separators_d, regions_fully, regions_without_separators, polygons_of_marginals, contours_tables = self.run_boxes_full_layout(image_page, textline_mask_tot, text_regions_p, slope_deskew, num_col_classifier, img_only_regions, table_prediction, erosion_hurts)
text_only = ((img_revised_tab[:, :] == 1)) * 1 text_only = ((img_revised_tab[:, :] == 1)) * 1
if np.abs(slope_deskew) >= SLOPE_THRESHOLD: if np.abs(slope_deskew) >= SLOPE_THRESHOLD:
text_only_d = ((text_regions_p_1_n[:, :] == 1)) * 1 text_only_d = ((text_regions_p_1_n[:, :] == 1)) * 1
@ -2486,6 +2486,7 @@ class Eynollah:
# print(len(contours_only_text_parent_h),len(contours_only_text_parent_h_d_ordered),'contours_only_text_parent_h') # print(len(contours_only_text_parent_h),len(contours_only_text_parent_h_d_ordered),'contours_only_text_parent_h')
pixel_lines = 6 pixel_lines = 6
if not self.headers_off: if not self.headers_off:
if np.abs(slope_deskew) < SLOPE_THRESHOLD: if np.abs(slope_deskew) < SLOPE_THRESHOLD:
num_col, _, matrix_of_lines_ch, splitter_y_new, _ = find_number_of_columns_in_document(np.repeat(text_regions_p[:, :, np.newaxis], 3, axis=2), num_col_classifier, self.tables, pixel_lines, contours_only_text_parent_h) num_col, _, matrix_of_lines_ch, splitter_y_new, _ = find_number_of_columns_in_document(np.repeat(text_regions_p[:, :, np.newaxis], 3, axis=2), num_col_classifier, self.tables, pixel_lines, contours_only_text_parent_h)