diff --git a/qurator/eynollah/utils/__init__.py b/qurator/eynollah/utils/__init__.py index a6eb58f..a189fa1 100644 --- a/qurator/eynollah/utils/__init__.py +++ b/qurator/eynollah/utils/__init__.py @@ -348,7 +348,8 @@ def boosting_headers_by_longshot_region_segmentation(textregion_pre_p, textregio # headers_in_longshot= ( (textregion_pre_np[:,:,0]==2) | (textregion_pre_np[:,:,0]==1) )*1 textregion_pre_p[:, :, 0][(headers_in_longshot[:, :] == 1) & (textregion_pre_p[:, :, 0] != 4)] = 2 textregion_pre_p[:, :, 0][textregion_pre_p[:, :, 0] == 1] = 0 - # textregion_pre_p[:,:,0][( img_only_text[:,:]==1) & (textregion_pre_p[:,:,0]!=7) & (textregion_pre_p[:,:,0]!=2)]=1 # eralier it was so, but by this manner the drop capitals are alse deleted + # earlier it was so, but by this manner the drop capitals are also deleted + # textregion_pre_p[:,:,0][( img_only_text[:,:]==1) & (textregion_pre_p[:,:,0]!=7) & (textregion_pre_p[:,:,0]!=2)]=1 textregion_pre_p[:, :, 0][(img_only_text[:, :] == 1) & (textregion_pre_p[:, :, 0] != 7) & (textregion_pre_p[:, :, 0] != 4) & (textregion_pre_p[:, :, 0] != 2)] = 1 return textregion_pre_p diff --git a/qurator/eynollah/utils/contour.py b/qurator/eynollah/utils/contour.py index ce400b2..3209731 100644 --- a/qurator/eynollah/utils/contour.py +++ b/qurator/eynollah/utils/contour.py @@ -50,7 +50,7 @@ def filter_contours_area_of_image(image, contours, hierarchy, max_area, min_area polygon = geometry.Polygon([point[0] for point in c]) area = polygon.area - if area >= min_area * np.prod(image.shape[:2]) and area <= max_area * np.prod(image.shape[:2]) and hierarchy[0][jv][3] == -1: # and hirarchy[0][jv][3]==-1 : + if area >= min_area * np.prod(image.shape[:2]) and area <= max_area * np.prod(image.shape[:2]) and hierarchy[0][jv][3] == -1: # and hierarchy[0][jv][3]==-1 : found_polygons_early.append(np.array([[point] for point in polygon.exterior.coords], dtype=np.uint)) jv += 1 return found_polygons_early @@ -68,7 +68,7 @@ def filter_contours_area_of_image_tables(image, contours, hierarchy, max_area, m area = polygon.area ##print(np.prod(thresh.shape[:2])) # Check that polygon has area greater than minimal area - # print(hierarchy[0][jv][3],hirarchy ) + # print(hierarchy[0][jv][3],hierarchy ) if area >= min_area * np.prod(image.shape[:2]) and area <= max_area * np.prod(image.shape[:2]): # and hierarchy[0][jv][3]==-1 : # print(c[0][0][1]) found_polygons_early.append(np.array([[point] for point in polygon.exterior.coords], dtype=np.int32))