From 7cbca79f1676da3bead00acaba44157dab5de05c Mon Sep 17 00:00:00 2001 From: vahidrezanezhad Date: Fri, 1 Dec 2023 23:40:47 +0100 Subject: [PATCH] replacing images cotour with bounding box --- qurator/eynollah/eynollah.py | 32 +++++++++++++++++--------------- qurator/eynollah/writer.py | 16 ++++++++++++---- 2 files changed, 29 insertions(+), 19 deletions(-) diff --git a/qurator/eynollah/eynollah.py b/qurator/eynollah/eynollah.py index 5a8adeb..e3e3a20 100644 --- a/qurator/eynollah/eynollah.py +++ b/qurator/eynollah/eynollah.py @@ -1693,17 +1693,18 @@ class Eynollah: image_boundary_of_doc = np.zeros((text_regions_p_true.shape[0], text_regions_p_true.shape[1])) - image_boundary_of_doc[:20, :] = 1 - image_boundary_of_doc[text_regions_p_true.shape[0]-20:text_regions_p_true.shape[0], :] = 1 + ###image_boundary_of_doc[:6, :] = 1 + ###image_boundary_of_doc[text_regions_p_true.shape[0]-6:text_regions_p_true.shape[0], :] = 1 - image_boundary_of_doc[:, :20] = 1 - image_boundary_of_doc[:, text_regions_p_true.shape[1]-20:text_regions_p_true.shape[1]] = 1 + ###image_boundary_of_doc[:, :6] = 1 + ###image_boundary_of_doc[:, text_regions_p_true.shape[1]-6:text_regions_p_true.shape[1]] = 1 #plt.imshow(image_boundary_of_doc) #plt.show() polygons_of_images_fin = [] for ploy_img_ind in polygons_of_images: + """ test_poly_image = np.zeros((text_regions_p_true.shape[0], text_regions_p_true.shape[1])) test_poly_image = cv2.fillPoly(test_poly_image, pts = [ploy_img_ind], color=(1,1,1)) @@ -1713,20 +1714,21 @@ class Eynollah: test_poly_image_intersected_area = test_poly_image_intersected_area.sum() if test_poly_image_intersected_area==0: - polygons_of_images_fin.append(ploy_img_ind) + ##polygons_of_images_fin.append(ploy_img_ind) - #x, y, w, h = cv2.boundingRect(ploy_img_ind) - #box = [x, y, w, h] - #_, page_coord = crop_image_inside_box(box, text_regions_p_true) + x, y, w, h = cv2.boundingRect(ploy_img_ind) + box = [x, y, w, h] + _, page_coord_img = crop_image_inside_box(box, text_regions_p_true) #cont_page.append(np.array([[page_coord[2], page_coord[0]], [page_coord[3], page_coord[0]], [page_coord[3], page_coord[1]], [page_coord[2], page_coord[1]]])) - #polygons_of_images_fin.append(np.array(cont_page)) - #plt.imshow(test_poly_image) - #plt.show() - - - - + polygons_of_images_fin.append(np.array([[page_coord_img[2], page_coord_img[0]], [page_coord_img[3], page_coord_img[0]], [page_coord_img[3], page_coord_img[1]], [page_coord_img[2], page_coord_img[1]]]) ) + """ + x, y, w, h = cv2.boundingRect(ploy_img_ind) + box = [x, y, w, h] + _, page_coord_img = crop_image_inside_box(box, text_regions_p_true) + #cont_page.append(np.array([[page_coord[2], page_coord[0]], [page_coord[3], page_coord[0]], [page_coord[3], page_coord[1]], [page_coord[2], page_coord[1]]])) + + polygons_of_images_fin.append(np.array([[page_coord_img[2], page_coord_img[0]], [page_coord_img[3], page_coord_img[0]], [page_coord_img[3], page_coord_img[1]], [page_coord_img[2], page_coord_img[1]]]) ) return text_regions_p_true, erosion_hurts, polygons_lines_xml, polygons_of_images_fin, image_page, page_coord, cont_page def get_regions_light_v(self,img,is_image_enhanced, num_col_classifier): diff --git a/qurator/eynollah/writer.py b/qurator/eynollah/writer.py index f537f65..4487af5 100644 --- a/qurator/eynollah/writer.py +++ b/qurator/eynollah/writer.py @@ -172,10 +172,18 @@ class EynollahXmlWriter(): page.add_ImageRegion(img_region) points_co = '' for lmm in range(len(found_polygons_text_region_img[mm])): - points_co += str(int((found_polygons_text_region_img[mm][lmm,0,0] + page_coord[2]) / self.scale_x)) - points_co += ',' - points_co += str(int((found_polygons_text_region_img[mm][lmm,0,1] + page_coord[0]) / self.scale_y)) - points_co += ' ' + try: + points_co += str(int((found_polygons_text_region_img[mm][lmm,0,0] + page_coord[2]) / self.scale_x)) + points_co += ',' + points_co += str(int((found_polygons_text_region_img[mm][lmm,0,1] + page_coord[0]) / self.scale_y)) + points_co += ' ' + except: + + points_co += str(int((found_polygons_text_region_img[mm][lmm][0] + page_coord[2])/ self.scale_x )) + points_co += ',' + points_co += str(int((found_polygons_text_region_img[mm][lmm][1] + page_coord[0])/ self.scale_y )) + points_co += ' ' + img_region.get_Coords().set_points(points_co[:-1]) for mm in range(len(polygons_lines_to_be_written_in_xml)):