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

avoid pulling unused 'image_page_rotated' through functions

Browse source
This commit is contained in:
Robert Sachunsky 2025-08-26 21:05:40 +02:00
parent 142ac8825e
commit dbbf1073df
2 changed files with 25 additions and 29 deletions
Download patch file Download diff file Expand all files Collapse all files

48
src/eynollah/eynollah.py
View file

@ -1521,7 +1521,7 @@ class Eynollah:
self.logger.debug("exit extract_text_regions") self.logger.debug("exit extract_text_regions")
return prediction_regions, prediction_regions2 return prediction_regions, prediction_regions2
def get_slopes_and_deskew_new_light2(self, contours, contours_par, textline_mask_tot, image_page_rotated, boxes, slope_deskew): def get_slopes_and_deskew_new_light2(self, contours, contours_par, textline_mask_tot, boxes, slope_deskew):
polygons_of_textlines = return_contours_of_interested_region(textline_mask_tot,1,0.00001) polygons_of_textlines = return_contours_of_interested_region(textline_mask_tot,1,0.00001)
M_main_tot = [cv2.moments(polygons_of_textlines[j]) M_main_tot = [cv2.moments(polygons_of_textlines[j])
@ -1549,13 +1549,12 @@ class Eynollah:
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
def get_slopes_and_deskew_new_light(self, contours, contours_par, textline_mask_tot, image_page_rotated, boxes, slope_deskew): def get_slopes_and_deskew_new_light(self, contours, contours_par, textline_mask_tot, boxes, slope_deskew):
if not len(contours): if not len(contours):
return [], [], [], [], [], [], [] return [], [], [], [], [], [], []
self.logger.debug("enter get_slopes_and_deskew_new_light") self.logger.debug("enter get_slopes_and_deskew_new_light")
results = self.executor.map(partial(do_work_of_slopes_new_light, results = self.executor.map(partial(do_work_of_slopes_new_light,
textline_mask_tot_ea=textline_mask_tot, textline_mask_tot_ea=textline_mask_tot,
image_page_rotated=image_page_rotated,
slope_deskew=slope_deskew,textline_light=self.textline_light, slope_deskew=slope_deskew,textline_light=self.textline_light,
logger=self.logger,), logger=self.logger,),
boxes, contours, contours_par, range(len(contours_par))) boxes, contours, contours_par, range(len(contours_par)))
@ -1563,13 +1562,12 @@ class Eynollah:
self.logger.debug("exit get_slopes_and_deskew_new_light") self.logger.debug("exit get_slopes_and_deskew_new_light")
return tuple(zip(*results)) return tuple(zip(*results))
def get_slopes_and_deskew_new(self, contours, contours_par, textline_mask_tot, image_page_rotated, boxes, slope_deskew): def get_slopes_and_deskew_new(self, contours, contours_par, textline_mask_tot, boxes, slope_deskew):
if not len(contours): if not len(contours):
return [], [], [], [], [], [], [] return [], [], [], [], [], [], []
self.logger.debug("enter get_slopes_and_deskew_new") self.logger.debug("enter get_slopes_and_deskew_new")
results = self.executor.map(partial(do_work_of_slopes_new, results = self.executor.map(partial(do_work_of_slopes_new,
textline_mask_tot_ea=textline_mask_tot, textline_mask_tot_ea=textline_mask_tot,
image_page_rotated=image_page_rotated,
slope_deskew=slope_deskew, slope_deskew=slope_deskew,
MAX_SLOPE=MAX_SLOPE, MAX_SLOPE=MAX_SLOPE,
KERNEL=KERNEL, KERNEL=KERNEL,
@ -1580,13 +1578,12 @@ class Eynollah:
self.logger.debug("exit get_slopes_and_deskew_new") self.logger.debug("exit get_slopes_and_deskew_new")
return tuple(zip(*results)) return tuple(zip(*results))
def get_slopes_and_deskew_new_curved(self, contours, contours_par, textline_mask_tot, image_page_rotated, boxes, mask_texts_only, num_col, scale_par, slope_deskew): def get_slopes_and_deskew_new_curved(self, contours, contours_par, textline_mask_tot, boxes, mask_texts_only, num_col, scale_par, slope_deskew):
if not len(contours): if not len(contours):
return [], [], [], [], [], [], [] return [], [], [], [], [], [], []
self.logger.debug("enter get_slopes_and_deskew_new_curved") self.logger.debug("enter get_slopes_and_deskew_new_curved")
results = self.executor.map(partial(do_work_of_slopes_new_curved, results = self.executor.map(partial(do_work_of_slopes_new_curved,
textline_mask_tot_ea=textline_mask_tot, textline_mask_tot_ea=textline_mask_tot,
image_page_rotated=image_page_rotated,
mask_texts_only=mask_texts_only, mask_texts_only=mask_texts_only,
num_col=num_col, num_col=num_col,
scale_par=scale_par, scale_par=scale_par,
@ -2935,10 +2932,10 @@ class Eynollah:
return slope_deskew return slope_deskew
def run_marginals( def run_marginals(
self, image_page, textline_mask_tot_ea, mask_images, mask_lines, self, textline_mask_tot_ea, mask_images, mask_lines,
num_col_classifier, slope_deskew, text_regions_p_1, table_prediction): num_col_classifier, slope_deskew, text_regions_p_1, table_prediction):
image_page_rotated, textline_mask_tot = image_page[:, :], textline_mask_tot_ea[:, :] textline_mask_tot = textline_mask_tot_ea[:, :]
textline_mask_tot[mask_images[:, :] == 1] = 0 textline_mask_tot[mask_images[:, :] == 1] = 0
text_regions_p_1[mask_lines[:, :] == 1] = 3 text_regions_p_1[mask_lines[:, :] == 1] = 3
@ -2957,10 +2954,7 @@ class Eynollah:
except Exception as e: except Exception as e:
self.logger.error("exception %s", e) self.logger.error("exception %s", e)
if self.plotter: return textline_mask_tot, text_regions_p
self.plotter.save_plot_of_layout_main_all(text_regions_p, image_page)
self.plotter.save_plot_of_layout_main(text_regions_p, image_page)
return textline_mask_tot, text_regions_p, image_page_rotated
def run_boxes_no_full_layout( def run_boxes_no_full_layout(
self, image_page, textline_mask_tot, text_regions_p, self, image_page, textline_mask_tot, text_regions_p,
@ -3112,7 +3106,7 @@ class Eynollah:
text_regions_p[:,:][table_prediction[:,:]==1] = 10 text_regions_p[:,:][table_prediction[:,:]==1] = 10
img_revised_tab = text_regions_p[:,:] img_revised_tab = text_regions_p[:,:]
if np.abs(slope_deskew) >= SLOPE_THRESHOLD: if np.abs(slope_deskew) >= SLOPE_THRESHOLD:
image_page_rotated_n, textline_mask_tot_d, text_regions_p_1_n, table_prediction_n = \ _, textline_mask_tot_d, text_regions_p_1_n, table_prediction_n = \
rotation_not_90_func(image_page, textline_mask_tot, text_regions_p, table_prediction, slope_deskew) rotation_not_90_func(image_page, textline_mask_tot, text_regions_p, table_prediction, 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])
@ -3132,7 +3126,7 @@ class Eynollah:
else: else:
if np.abs(slope_deskew) >= SLOPE_THRESHOLD: if np.abs(slope_deskew) >= SLOPE_THRESHOLD:
image_page_rotated_n, textline_mask_tot_d, text_regions_p_1_n, table_prediction_n = \ _, textline_mask_tot_d, text_regions_p_1_n, table_prediction_n = \
rotation_not_90_func(image_page, textline_mask_tot, text_regions_p, table_prediction, slope_deskew) rotation_not_90_func(image_page, textline_mask_tot, text_regions_p, table_prediction, 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])
@ -4008,9 +4002,12 @@ class Eynollah:
text_regions_p_1 = resize_image(text_regions_p_1,img_h_new, img_w_new ) text_regions_p_1 = resize_image(text_regions_p_1,img_h_new, img_w_new )
table_prediction = resize_image(table_prediction,img_h_new, img_w_new ) table_prediction = resize_image(table_prediction,img_h_new, img_w_new )
textline_mask_tot, text_regions_p, image_page_rotated = \ textline_mask_tot, text_regions_p = \
self.run_marginals(image_page, textline_mask_tot_ea, mask_images, mask_lines, self.run_marginals(textline_mask_tot_ea, mask_images, mask_lines,
num_col_classifier, slope_deskew, text_regions_p_1, table_prediction) num_col_classifier, slope_deskew, text_regions_p_1, table_prediction)
if self.plotter:
self.plotter.save_plot_of_layout_main_all(text_regions_p, image_page)
self.plotter.save_plot_of_layout_main(text_regions_p, image_page)
if self.light_version and num_col_classifier in (1,2): if self.light_version and num_col_classifier in (1,2):
image_page = resize_image(image_page,org_h_l_m, org_w_l_m ) image_page = resize_image(image_page,org_h_l_m, org_w_l_m )
@ -4019,7 +4016,6 @@ class Eynollah:
textline_mask_tot = resize_image(textline_mask_tot,org_h_l_m, org_w_l_m ) textline_mask_tot = resize_image(textline_mask_tot,org_h_l_m, org_w_l_m )
text_regions_p_1 = resize_image(text_regions_p_1,org_h_l_m, org_w_l_m ) text_regions_p_1 = resize_image(text_regions_p_1,org_h_l_m, org_w_l_m )
table_prediction = resize_image(table_prediction,org_h_l_m, org_w_l_m ) table_prediction = resize_image(table_prediction,org_h_l_m, org_w_l_m )
image_page_rotated = resize_image(image_page_rotated,org_h_l_m, org_w_l_m )
self.logger.info("detection of marginals took %.1fs", time.time() - t1) self.logger.info("detection of marginals took %.1fs", time.time() - t1)
#print("text region early 2 marginal in %.1fs", time.time() - t0) #print("text region early 2 marginal in %.1fs", time.time() - t0)
@ -4195,11 +4191,11 @@ class Eynollah:
all_found_textline_polygons, boxes_text, txt_con_org, contours_only_text_parent, \ all_found_textline_polygons, boxes_text, txt_con_org, contours_only_text_parent, \
all_box_coord, index_by_text_par_con, slopes = self.get_slopes_and_deskew_new_light2( all_box_coord, index_by_text_par_con, slopes = self.get_slopes_and_deskew_new_light2(
txt_con_org, contours_only_text_parent, textline_mask_tot_ea_org, txt_con_org, contours_only_text_parent, textline_mask_tot_ea_org,
image_page_rotated, boxes_text, slope_deskew) boxes_text, slope_deskew)
all_found_textline_polygons_marginals, boxes_marginals, _, polygons_of_marginals, \ all_found_textline_polygons_marginals, boxes_marginals, _, polygons_of_marginals, \
all_box_coord_marginals, _, slopes_marginals = self.get_slopes_and_deskew_new_light2( all_box_coord_marginals, _, slopes_marginals = self.get_slopes_and_deskew_new_light2(
polygons_of_marginals, polygons_of_marginals, textline_mask_tot_ea_org, polygons_of_marginals, polygons_of_marginals, textline_mask_tot_ea_org,
image_page_rotated, boxes_marginals, slope_deskew) boxes_marginals, slope_deskew)
#slopes, all_found_textline_polygons, boxes_text, txt_con_org, contours_only_text_parent, index_by_text_par_con = \ #slopes, all_found_textline_polygons, boxes_text, txt_con_org, contours_only_text_parent, index_by_text_par_con = \
# self.delete_regions_without_textlines(slopes, all_found_textline_polygons, # self.delete_regions_without_textlines(slopes, all_found_textline_polygons,
@ -4219,11 +4215,11 @@ class Eynollah:
all_found_textline_polygons, boxes_text, txt_con_org, contours_only_text_parent, all_box_coord, \ all_found_textline_polygons, boxes_text, txt_con_org, contours_only_text_parent, all_box_coord, \
index_by_text_par_con, slopes = self.get_slopes_and_deskew_new_light( index_by_text_par_con, slopes = self.get_slopes_and_deskew_new_light(
txt_con_org, contours_only_text_parent, textline_mask_tot_ea, txt_con_org, contours_only_text_parent, textline_mask_tot_ea,
image_page_rotated, boxes_text, slope_deskew) boxes_text, slope_deskew)
all_found_textline_polygons_marginals, boxes_marginals, _, polygons_of_marginals, \ all_found_textline_polygons_marginals, boxes_marginals, _, polygons_of_marginals, \
all_box_coord_marginals, _, slopes_marginals = self.get_slopes_and_deskew_new_light( all_box_coord_marginals, _, slopes_marginals = self.get_slopes_and_deskew_new_light(
polygons_of_marginals, polygons_of_marginals, textline_mask_tot_ea, polygons_of_marginals, polygons_of_marginals, textline_mask_tot_ea,
image_page_rotated, boxes_marginals, slope_deskew) boxes_marginals, slope_deskew)
#all_found_textline_polygons = self.filter_contours_inside_a_bigger_one( #all_found_textline_polygons = self.filter_contours_inside_a_bigger_one(
# all_found_textline_polygons, textline_mask_tot_ea_org, type_contour="textline") # all_found_textline_polygons, textline_mask_tot_ea_org, type_contour="textline")
else: else:
@ -4231,25 +4227,25 @@ class Eynollah:
all_found_textline_polygons, boxes_text, txt_con_org, contours_only_text_parent, \ all_found_textline_polygons, boxes_text, txt_con_org, contours_only_text_parent, \
all_box_coord, index_by_text_par_con, slopes = self.get_slopes_and_deskew_new( all_box_coord, index_by_text_par_con, slopes = self.get_slopes_and_deskew_new(
txt_con_org, contours_only_text_parent, textline_mask_tot_ea, txt_con_org, contours_only_text_parent, textline_mask_tot_ea,
image_page_rotated, boxes_text, slope_deskew) boxes_text, slope_deskew)
all_found_textline_polygons_marginals, boxes_marginals, _, polygons_of_marginals, \ all_found_textline_polygons_marginals, boxes_marginals, _, polygons_of_marginals, \
all_box_coord_marginals, _, slopes_marginals = self.get_slopes_and_deskew_new( all_box_coord_marginals, _, slopes_marginals = self.get_slopes_and_deskew_new(
polygons_of_marginals, polygons_of_marginals, textline_mask_tot_ea, polygons_of_marginals, polygons_of_marginals, textline_mask_tot_ea,
image_page_rotated, boxes_marginals, slope_deskew) boxes_marginals, slope_deskew)
else: else:
scale_param = 1 scale_param = 1
textline_mask_tot_ea_erode = cv2.erode(textline_mask_tot_ea, kernel=KERNEL, iterations=2) textline_mask_tot_ea_erode = cv2.erode(textline_mask_tot_ea, kernel=KERNEL, iterations=2)
all_found_textline_polygons, boxes_text, txt_con_org, contours_only_text_parent, \ all_found_textline_polygons, boxes_text, txt_con_org, contours_only_text_parent, \
all_box_coord, index_by_text_par_con, slopes = self.get_slopes_and_deskew_new_curved( all_box_coord, index_by_text_par_con, slopes = self.get_slopes_and_deskew_new_curved(
txt_con_org, contours_only_text_parent, textline_mask_tot_ea_erode, txt_con_org, contours_only_text_parent, textline_mask_tot_ea_erode,
image_page_rotated, boxes_text, text_only, boxes_text, text_only,
num_col_classifier, scale_param, slope_deskew) num_col_classifier, scale_param, slope_deskew)
all_found_textline_polygons = small_textlines_to_parent_adherence2( all_found_textline_polygons = small_textlines_to_parent_adherence2(
all_found_textline_polygons, textline_mask_tot_ea, num_col_classifier) all_found_textline_polygons, textline_mask_tot_ea, num_col_classifier)
all_found_textline_polygons_marginals, boxes_marginals, _, polygons_of_marginals, \ all_found_textline_polygons_marginals, boxes_marginals, _, polygons_of_marginals, \
all_box_coord_marginals, _, slopes_marginals = self.get_slopes_and_deskew_new_curved( all_box_coord_marginals, _, slopes_marginals = self.get_slopes_and_deskew_new_curved(
polygons_of_marginals, polygons_of_marginals, textline_mask_tot_ea_erode, polygons_of_marginals, polygons_of_marginals, textline_mask_tot_ea_erode,
image_page_rotated, boxes_marginals, text_only, boxes_marginals, text_only,
num_col_classifier, scale_param, slope_deskew) num_col_classifier, scale_param, slope_deskew)
all_found_textline_polygons_marginals = small_textlines_to_parent_adherence2( all_found_textline_polygons_marginals = small_textlines_to_parent_adherence2(
all_found_textline_polygons_marginals, textline_mask_tot_ea, num_col_classifier) all_found_textline_polygons_marginals, textline_mask_tot_ea, num_col_classifier)

6
src/eynollah/utils/separate_lines.py
View file

@ -1532,7 +1532,7 @@ def get_smallest_skew(img, sigma_des, angles, logger=None, plotter=None, map=map
def do_work_of_slopes_new( def do_work_of_slopes_new(
box_text, contour, contour_par, index_r_con, box_text, contour, contour_par, index_r_con,
textline_mask_tot_ea, image_page_rotated, slope_deskew, textline_mask_tot_ea, slope_deskew,
logger=None, MAX_SLOPE=999, KERNEL=None, plotter=None logger=None, MAX_SLOPE=999, KERNEL=None, plotter=None
): ):
if KERNEL is None: if KERNEL is None:
@ -1590,7 +1590,7 @@ def do_work_of_slopes_new(
def do_work_of_slopes_new_curved( def do_work_of_slopes_new_curved(
box_text, contour, contour_par, index_r_con, box_text, contour, contour_par, index_r_con,
textline_mask_tot_ea, image_page_rotated, mask_texts_only, num_col, scale_par, slope_deskew, textline_mask_tot_ea, mask_texts_only, num_col, scale_par, slope_deskew,
logger=None, MAX_SLOPE=999, KERNEL=None, plotter=None logger=None, MAX_SLOPE=999, KERNEL=None, plotter=None
): ):
if KERNEL is None: if KERNEL is None:
@ -1679,7 +1679,7 @@ def do_work_of_slopes_new_curved(
def do_work_of_slopes_new_light( def do_work_of_slopes_new_light(
box_text, contour, contour_par, index_r_con, box_text, contour, contour_par, index_r_con,
textline_mask_tot_ea, image_page_rotated, slope_deskew, textline_light, textline_mask_tot_ea, slope_deskew, textline_light,
logger=None logger=None
): ):
if logger is None: if logger is None: