qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-09-17 21:29:56 +02:00
Code Issues Projects Releases Wiki Activity

use box2rect instead of crop_image_inside_box when no image needed

Browse source
This commit is contained in:
Robert Sachunsky 2025-08-26 21:02:43 +02:00
parent 892ff41e38
commit 142ac8825e
2 changed files with 10 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

8
src/eynollah/eynollah.py
View file

@ -98,6 +98,8 @@ from .utils.resize import resize_image
from .utils import ( from .utils import (
boosting_headers_by_longshot_region_segmentation, boosting_headers_by_longshot_region_segmentation,
crop_image_inside_box, crop_image_inside_box,
box2rect,
box2slice,
find_num_col, find_num_col,
otsu_copy_binary, otsu_copy_binary,
put_drop_out_from_only_drop_model, put_drop_out_from_only_drop_model,
@ -1542,7 +1544,7 @@ class Eynollah:
all_found_textline_polygons.append(textlines_ins[::-1]) all_found_textline_polygons.append(textlines_ins[::-1])
slopes.append(slope_deskew) slopes.append(slope_deskew)
_, crop_coor = crop_image_inside_box(boxes[index],image_page_rotated) crop_coor = box2rect(boxes[index])
all_box_coord.append(crop_coor) all_box_coord.append(crop_coor)
return all_found_textline_polygons, boxes, contours, contours_par, all_box_coord, np.array(range(len(contours_par))), slopes return all_found_textline_polygons, boxes, contours, contours_par, all_box_coord, np.array(range(len(contours_par))), slopes
@ -1754,7 +1756,7 @@ class Eynollah:
##polygons_of_images_fin.append(ploy_img_ind) ##polygons_of_images_fin.append(ploy_img_ind)
box = cv2.boundingRect(ploy_img_ind) box = cv2.boundingRect(ploy_img_ind)
_, page_coord_img = crop_image_inside_box(box, text_regions_p_true) page_coord_img = box2rect(box)
# cont_page.append(np.array([[page_coord[2], page_coord[0]], # cont_page.append(np.array([[page_coord[2], page_coord[0]],
# [page_coord[3], page_coord[0]], # [page_coord[3], page_coord[0]],
# [page_coord[3], page_coord[1]], # [page_coord[3], page_coord[1]],
@ -1768,7 +1770,7 @@ class Eynollah:
if h < 150 or w < 150: if h < 150 or w < 150:
pass pass
else: else:
_, page_coord_img = crop_image_inside_box(box, text_regions_p_true) page_coord_img = box2rect(box)
# cont_page.append(np.array([[page_coord[2], page_coord[0]], # cont_page.append(np.array([[page_coord[2], page_coord[0]],
# [page_coord[3], page_coord[0]], # [page_coord[3], page_coord[0]],
# [page_coord[3], page_coord[1]], # [page_coord[3], page_coord[1]],

8
src/eynollah/utils/separate_lines.py
View file

@ -18,6 +18,8 @@ from .contour import (
from . import ( from . import (
find_num_col_deskew, find_num_col_deskew,
crop_image_inside_box, crop_image_inside_box,
box2rect,
box2slice,
) )
def dedup_separate_lines(img_patch, contour_text_interest, thetha, axis): def dedup_separate_lines(img_patch, contour_text_interest, thetha, axis):
@ -1540,7 +1542,7 @@ def do_work_of_slopes_new(
logger.debug('enter do_work_of_slopes_new') logger.debug('enter do_work_of_slopes_new')
x, y, w, h = box_text x, y, w, h = box_text
_, crop_coor = crop_image_inside_box(box_text, image_page_rotated) crop_coor = box2rect(box_text)
mask_textline = np.zeros(textline_mask_tot_ea.shape) mask_textline = np.zeros(textline_mask_tot_ea.shape)
mask_textline = cv2.fillPoly(mask_textline, pts=[contour], color=(1,1,1)) mask_textline = cv2.fillPoly(mask_textline, pts=[contour], color=(1,1,1))
all_text_region_raw = textline_mask_tot_ea * mask_textline all_text_region_raw = textline_mask_tot_ea * mask_textline
@ -1631,7 +1633,7 @@ def do_work_of_slopes_new_curved(
slope_for_all = slope_deskew slope_for_all = slope_deskew
slope = slope_for_all slope = slope_for_all
_, crop_coor = crop_image_inside_box(box_text, image_page_rotated) crop_coor = box2rect(box_text)
if abs(slope_for_all) < 45: if abs(slope_for_all) < 45:
textline_region_in_image = np.zeros(textline_mask_tot_ea.shape) textline_region_in_image = np.zeros(textline_mask_tot_ea.shape)
@ -1685,7 +1687,7 @@ def do_work_of_slopes_new_light(
logger.debug('enter do_work_of_slopes_new_light') logger.debug('enter do_work_of_slopes_new_light')
x, y, w, h = box_text x, y, w, h = box_text
_, crop_coor = crop_image_inside_box(box_text, image_page_rotated) crop_coor = box2rect(box_text)
mask_textline = np.zeros(textline_mask_tot_ea.shape) mask_textline = np.zeros(textline_mask_tot_ea.shape)
mask_textline = cv2.fillPoly(mask_textline, pts=[contour], color=(1,1,1)) mask_textline = cv2.fillPoly(mask_textline, pts=[contour], color=(1,1,1))
all_text_region_raw = textline_mask_tot_ea * mask_textline all_text_region_raw = textline_mask_tot_ea * mask_textline