From 38a2d60fa2766aac3dc8f0412bb60315fa38ffdf Mon Sep 17 00:00:00 2001 From: vahidrezanezhad Date: Thu, 3 Apr 2025 12:47:27 +0200 Subject: [PATCH] Confidence value for textregions and in the case of not light version is set to zero. This is done to let the pipeline go through. It will be updated to return the correct value in upcomming commits --- src/eynollah/eynollah.py | 6 +++--- src/eynollah/utils/__init__.py | 9 +++++++-- 2 files changed, 10 insertions(+), 5 deletions(-) diff --git a/src/eynollah/eynollah.py b/src/eynollah/eynollah.py index 27003c2..eda2288 100644 --- a/src/eynollah/eynollah.py +++ b/src/eynollah/eynollah.py @@ -4486,6 +4486,7 @@ class Eynollah: self.get_regions_from_xy_2models(img_res, is_image_enhanced, num_col_classifier) self.logger.info("Textregion detection took %.1fs ", time.time() - t1) + confidence_matrix = np.zeros((text_regions_p_1.shape[:2])) t1 = time.time() num_col, num_col_classifier, img_only_regions, page_coord, image_page, mask_images, mask_lines, \ @@ -4719,8 +4720,8 @@ class Eynollah: #contours_only_text_parent = self.dilate_textregions_contours(contours_only_text_parent) else: - txt_con_org = get_textregion_contours_in_org_image( - contours_only_text_parent, self.image, slope_first) + txt_con_org , conf_contours_textregions = get_textregion_contours_in_org_image_light( + contours_only_text_parent, self.image, slope_first, confidence_matrix, map=self.executor.map) #print("text region early 4 in %.1fs", time.time() - t0) boxes_text, _ = get_text_region_boxes_by_given_contours(contours_only_text_parent) boxes_marginals, _ = get_text_region_boxes_by_given_contours(polygons_of_marginals) @@ -4812,7 +4813,6 @@ class Eynollah: if self.light_version: fun = check_any_text_region_in_model_one_is_main_or_header_light else: - conf_contours_textregions = None fun = check_any_text_region_in_model_one_is_main_or_header text_regions_p, contours_only_text_parent, contours_only_text_parent_h, all_box_coord, all_box_coord_h, \ all_found_textline_polygons, all_found_textline_polygons_h, slopes, slopes_h, \ diff --git a/src/eynollah/utils/__init__.py b/src/eynollah/utils/__init__.py index 5594fd0..bad114d 100644 --- a/src/eynollah/utils/__init__.py +++ b/src/eynollah/utils/__init__.py @@ -884,6 +884,9 @@ def check_any_text_region_in_model_one_is_main_or_header( contours_only_text_parent_main=[] contours_only_text_parent_head=[] + + conf_contours_main=[] + conf_contours_head=[] contours_only_text_parent_main_d=[] contours_only_text_parent_head_d=[] @@ -905,9 +908,11 @@ def check_any_text_region_in_model_one_is_main_or_header( all_box_coord_head.append(all_box_coord[ii]) slopes_head.append(slopes[ii]) all_found_textline_polygons_head.append(all_found_textline_polygons[ii]) + conf_contours_head.append(None) else: regions_model_1[:,:][(regions_model_1[:,:]==1) & (img[:,:,0]==255) ]=1 contours_only_text_parent_main.append(con) + conf_contours_main.append(conf_contours[ii]) if contours_only_text_parent_d_ordered is not None: contours_only_text_parent_main_d.append(contours_only_text_parent_d_ordered[ii]) all_box_coord_main.append(all_box_coord[ii]) @@ -927,8 +932,8 @@ def check_any_text_region_in_model_one_is_main_or_header( slopes_head, contours_only_text_parent_main_d, contours_only_text_parent_head_d, - None, - None) + conf_contours_main, + conf_contours_head) def check_any_text_region_in_model_one_is_main_or_header_light( regions_model_1, regions_model_full,