qurator-spk
/
eynollah
mirror of https://github.com/qurator-spk/eynollah.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

typo: s,contoures,contours,g

Browse Source
pull/23/head
Konstantin Baierer 4 years ago
parent ccd83e94b1
commit 5f2867bfcf
6 changed files with 33 additions and 33 deletions
Show Stats Download Patch File Download Diff File

20
qurator/eynollah/eynollah.py
Unescape Escape View File

@ -32,7 +32,7 @@ warnings.filterwarnings("ignore")
from .utils.contour import ( from .utils.contour import (
filter_contours_area_of_image, filter_contours_area_of_image,
find_contours_mean_y_diff, find_contours_mean_y_diff,
find_new_features_of_contoures, find_new_features_of_contours,
get_text_region_boxes_by_given_contours, get_text_region_boxes_by_given_contours,
get_textregion_contours_in_org_image, get_textregion_contours_in_org_image,
return_contours_of_image, return_contours_of_image,
@ -1124,8 +1124,8 @@ class Eynollah:
def do_order_of_regions_full_layout(self, contours_only_text_parent, contours_only_text_parent_h, boxes, textline_mask_tot): def do_order_of_regions_full_layout(self, contours_only_text_parent, contours_only_text_parent_h, boxes, textline_mask_tot):
self.logger.debug("enter do_order_of_regions_full_layout") self.logger.debug("enter do_order_of_regions_full_layout")
cx_text_only, cy_text_only, x_min_text_only, _, _, _, y_cor_x_min_main = find_new_features_of_contoures(contours_only_text_parent) cx_text_only, cy_text_only, x_min_text_only, _, _, _, y_cor_x_min_main = find_new_features_of_contours(contours_only_text_parent)
cx_text_only_h, cy_text_only_h, x_min_text_only_h, _, _, _, y_cor_x_min_main_h = find_new_features_of_contoures(contours_only_text_parent_h) cx_text_only_h, cy_text_only_h, x_min_text_only_h, _, _, _, y_cor_x_min_main_h = find_new_features_of_contours(contours_only_text_parent_h)
try: try:
arg_text_con = [] arg_text_con = []
@ -1274,7 +1274,7 @@ class Eynollah:
def do_order_of_regions_no_full_layout(self, contours_only_text_parent, contours_only_text_parent_h, boxes, textline_mask_tot): def do_order_of_regions_no_full_layout(self, contours_only_text_parent, contours_only_text_parent_h, boxes, textline_mask_tot):
self.logger.debug("enter do_order_of_regions_no_full_layout") self.logger.debug("enter do_order_of_regions_no_full_layout")
cx_text_only, cy_text_only, x_min_text_only, _, _, _, y_cor_x_min_main = find_new_features_of_contoures(contours_only_text_parent) cx_text_only, cy_text_only, x_min_text_only, _, _, _, y_cor_x_min_main = find_new_features_of_contours(contours_only_text_parent)
try: try:
arg_text_con = [] arg_text_con = []
@ -1655,8 +1655,8 @@ class Eynollah:
contours_only_text_parent = list(np.array(contours_only_text_parent)[index_con_parents]) contours_only_text_parent = list(np.array(contours_only_text_parent)[index_con_parents])
areas_cnt_text_parent = list(np.array(areas_cnt_text_parent)[index_con_parents]) areas_cnt_text_parent = list(np.array(areas_cnt_text_parent)[index_con_parents])
cx_bigest_big, cy_biggest_big, _, _, _, _, _ = find_new_features_of_contoures([contours_biggest]) cx_bigest_big, cy_biggest_big, _, _, _, _, _ = find_new_features_of_contours([contours_biggest])
cx_bigest, cy_biggest, _, _, _, _, _ = find_new_features_of_contoures(contours_only_text_parent) cx_bigest, cy_biggest, _, _, _, _, _ = find_new_features_of_contours(contours_only_text_parent)
contours_only_text_d, hir_on_text_d = return_contours_of_image(text_only_d) contours_only_text_d, hir_on_text_d = return_contours_of_image(text_only_d)
contours_only_text_parent_d = return_parent_contours(contours_only_text_d, hir_on_text_d) contours_only_text_parent_d = return_parent_contours(contours_only_text_d, hir_on_text_d)
@ -1669,8 +1669,8 @@ class Eynollah:
contours_only_text_parent_d=list(np.array(contours_only_text_parent_d)[index_con_parents_d] ) contours_only_text_parent_d=list(np.array(contours_only_text_parent_d)[index_con_parents_d] )
areas_cnt_text_d=list(np.array(areas_cnt_text_d)[index_con_parents_d] ) areas_cnt_text_d=list(np.array(areas_cnt_text_d)[index_con_parents_d] )
cx_bigest_d_big, cy_biggest_d_big, _, _, _, _, _ = find_new_features_of_contoures([contours_biggest_d]) cx_bigest_d_big, cy_biggest_d_big, _, _, _, _, _ = find_new_features_of_contours([contours_biggest_d])
cx_bigest_d, cy_biggest_d, _, _, _, _, _ = find_new_features_of_contoures(contours_only_text_parent_d) cx_bigest_d, cy_biggest_d, _, _, _, _, _ = find_new_features_of_contours(contours_only_text_parent_d)
try: try:
cx_bigest_d_last5 = cx_bigest_d[-5:] cx_bigest_d_last5 = cx_bigest_d[-5:]
cy_biggest_d_last5 = cy_biggest_d[-5:] cy_biggest_d_last5 = cy_biggest_d[-5:]
@ -1715,8 +1715,8 @@ class Eynollah:
contours_only_text_parent = list(np.array(contours_only_text_parent)[index_con_parents]) contours_only_text_parent = list(np.array(contours_only_text_parent)[index_con_parents])
areas_cnt_text_parent = list(np.array(areas_cnt_text_parent)[index_con_parents]) areas_cnt_text_parent = list(np.array(areas_cnt_text_parent)[index_con_parents])
cx_bigest_big, cy_biggest_big, _, _, _, _, _ = find_new_features_of_contoures([contours_biggest]) cx_bigest_big, cy_biggest_big, _, _, _, _, _ = find_new_features_of_contours([contours_biggest])
cx_bigest, cy_biggest, _, _, _, _, _ = find_new_features_of_contoures(contours_only_text_parent) cx_bigest, cy_biggest, _, _, _, _, _ = find_new_features_of_contours(contours_only_text_parent)
self.logger.debug('areas_cnt_text_parent %s', areas_cnt_text_parent) self.logger.debug('areas_cnt_text_parent %s', areas_cnt_text_parent)
# self.logger.debug('areas_cnt_text_parent_d %s', areas_cnt_text_parent_d) # self.logger.debug('areas_cnt_text_parent_d %s', areas_cnt_text_parent_d)
# self.logger.debug('len(contours_only_text_parent) %s', len(contours_only_text_parent_d)) # self.logger.debug('len(contours_only_text_parent) %s', len(contours_only_text_parent_d))

4
qurator/eynollah/plot.py
Unescape Escape View File

@ -153,10 +153,10 @@ class EynollahPlotter():
plt.legend(loc='best') plt.legend(loc='best')
plt.savefig(os.path.join(self.dir_of_all, self.image_filename_stem+'_rotation_angle.png')) plt.savefig(os.path.join(self.dir_of_all, self.image_filename_stem+'_rotation_angle.png'))
def write_images_into_directory(self, img_contoures, image_page): def write_images_into_directory(self, img_contours, image_page):
if self.dir_of_cropped_images is not None: if self.dir_of_cropped_images is not None:
index = 0 index = 0
for cont_ind in img_contoures: for cont_ind in img_contours:
x, y, w, h = cv2.boundingRect(cont_ind) x, y, w, h = cv2.boundingRect(cont_ind)
box = [x, y, w, h] box = [x, y, w, h]
croped_page, page_coord = crop_image_inside_box(box, image_page) croped_page, page_coord = crop_image_inside_box(box, image_page)

6
qurator/eynollah/utils/__init__.py
Unescape Escape View File

@ -10,7 +10,7 @@ from scipy.ndimage import gaussian_filter1d
from .is_nan import isNaN from .is_nan import isNaN
from .contour import (contours_in_same_horizon, from .contour import (contours_in_same_horizon,
find_new_features_of_contoures, find_new_features_of_contours,
return_contours_of_image, return_contours_of_image,
return_parent_contours) return_parent_contours)
@ -783,7 +783,7 @@ def putt_bb_of_drop_capitals_of_model_in_patches_in_layout(layout_in_patch):
return layout_in_patch return layout_in_patch
def check_any_text_region_in_model_one_is_main_or_header(regions_model_1,regions_model_full,contours_only_text_parent,all_box_coord,all_found_texline_polygons,slopes,contours_only_text_parent_d_ordered): def check_any_text_region_in_model_one_is_main_or_header(regions_model_1,regions_model_full,contours_only_text_parent,all_box_coord,all_found_texline_polygons,slopes,contours_only_text_parent_d_ordered):
cx_main,cy_main ,x_min_main , x_max_main, y_min_main ,y_max_main,y_corr_x_min_from_argmin=find_new_features_of_contoures(contours_only_text_parent) cx_main,cy_main ,x_min_main , x_max_main, y_min_main ,y_max_main,y_corr_x_min_from_argmin=find_new_features_of_contours(contours_only_text_parent)
length_con=x_max_main-x_min_main length_con=x_max_main-x_min_main
height_con=y_max_main-y_min_main height_con=y_max_main-y_min_main
@ -1267,7 +1267,7 @@ def combine_hor_lines_and_delete_cross_points_and_get_lines_features_back_new(im
ret, thresh = cv2.threshold(imgray, 0, 255, 0) ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_cross,_=cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE) contours_cross,_=cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
cx_cross,cy_cross ,_ , _, _ ,_,_=find_new_features_of_contoures(contours_cross) cx_cross,cy_cross ,_ , _, _ ,_,_=find_new_features_of_contours(contours_cross)
for ii in range(len(cx_cross)): for ii in range(len(cx_cross)):
img_p_in[int(cy_cross[ii])-30:int(cy_cross[ii])+30,int(cx_cross[ii])+5:int(cx_cross[ii])+40,0]=0 img_p_in[int(cy_cross[ii])-30:int(cy_cross[ii])+30,int(cx_cross[ii])+5:int(cx_cross[ii])+40,0]=0

2
qurator/eynollah/utils/contour.py
Unescape Escape View File

@ -75,7 +75,7 @@ def filter_contours_area_of_image_tables(image, contours, hirarchy, max_area, mi
jv += 1 jv += 1
return found_polygons_early return found_polygons_early
def find_new_features_of_contoures(contours_main): def find_new_features_of_contours(contours_main):
areas_main = np.array([cv2.contourArea(contours_main[j]) for j in range(len(contours_main))]) areas_main = np.array([cv2.contourArea(contours_main[j]) for j in range(len(contours_main))])
M_main = [cv2.moments(contours_main[j]) for j in range(len(contours_main))] M_main = [cv2.moments(contours_main[j]) for j in range(len(contours_main))]

30
qurator/eynollah/utils/drop_capitals.py
Unescape Escape View File

@ -1,7 +1,7 @@
import numpy as np import numpy as np
import cv2 import cv2
from .contour import ( from .contour import (
find_new_features_of_contoures, find_new_features_of_contours,
return_contours_of_image, return_contours_of_image,
return_parent_contours, return_parent_contours,
) )
@ -20,9 +20,9 @@ def adhere_drop_capital_region_into_corresponding_textline(
): ):
# print(np.shape(all_found_texline_polygons),np.shape(all_found_texline_polygons[3]),'all_found_texline_polygonsshape') # print(np.shape(all_found_texline_polygons),np.shape(all_found_texline_polygons[3]),'all_found_texline_polygonsshape')
# print(all_found_texline_polygons[3]) # print(all_found_texline_polygons[3])
cx_m, cy_m, _, _, _, _, _ = find_new_features_of_contoures(contours_only_text_parent) cx_m, cy_m, _, _, _, _, _ = find_new_features_of_contours(contours_only_text_parent)
cx_h, cy_h, _, _, _, _, _ = find_new_features_of_contoures(contours_only_text_parent_h) cx_h, cy_h, _, _, _, _, _ = find_new_features_of_contours(contours_only_text_parent_h)
cx_d, cy_d, _, _, y_min_d, y_max_d, _ = find_new_features_of_contoures(polygons_of_drop_capitals) cx_d, cy_d, _, _, y_min_d, y_max_d, _ = find_new_features_of_contours(polygons_of_drop_capitals)
img_con_all = np.zeros((text_regions_p.shape[0], text_regions_p.shape[1], 3)) img_con_all = np.zeros((text_regions_p.shape[0], text_regions_p.shape[1], 3))
for j_cont in range(len(contours_only_text_parent)): for j_cont in range(len(contours_only_text_parent)):
@ -87,9 +87,9 @@ def adhere_drop_capital_region_into_corresponding_textline(
region_final = region_with_intersected_drop[np.argmax(sum_pixels_of_intersection)] - 1 region_final = region_with_intersected_drop[np.argmax(sum_pixels_of_intersection)] - 1
# print(region_final,'region_final') # print(region_final,'region_final')
# cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contoures(all_found_texline_polygons[int(region_final)]) # cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contours(all_found_texline_polygons[int(region_final)])
try: try:
cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contoures(all_found_texline_polygons[int(region_final)]) cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contours(all_found_texline_polygons[int(region_final)])
# print(all_box_coord[j_cont]) # print(all_box_coord[j_cont])
# print(cx_t) # print(cx_t)
# print(cy_t) # print(cy_t)
@ -141,9 +141,9 @@ def adhere_drop_capital_region_into_corresponding_textline(
# areas_main=np.array([cv2.contourArea(all_found_texline_polygons[int(region_final)][0][j] ) for j in range(len(all_found_texline_polygons[int(region_final)]))]) # areas_main=np.array([cv2.contourArea(all_found_texline_polygons[int(region_final)][0][j] ) for j in range(len(all_found_texline_polygons[int(region_final)]))])
# cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contoures(all_found_texline_polygons[int(region_final)]) # cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contours(all_found_texline_polygons[int(region_final)])
cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contoures(all_found_texline_polygons[int(region_final)]) cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contours(all_found_texline_polygons[int(region_final)])
# print(all_box_coord[j_cont]) # print(all_box_coord[j_cont])
# print(cx_t) # print(cx_t)
# print(cy_t) # print(cy_t)
@ -191,7 +191,7 @@ def adhere_drop_capital_region_into_corresponding_textline(
# print(cx_t,'print') # print(cx_t,'print')
try: try:
# print(all_found_texline_polygons[j_cont][0]) # print(all_found_texline_polygons[j_cont][0])
cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contoures(all_found_texline_polygons[int(region_final)]) cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contours(all_found_texline_polygons[int(region_final)])
# print(all_box_coord[j_cont]) # print(all_box_coord[j_cont])
# print(cx_t) # print(cx_t)
# print(cy_t) # print(cy_t)
@ -238,7 +238,7 @@ def adhere_drop_capital_region_into_corresponding_textline(
else: else:
pass pass
##cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contoures(all_found_texline_polygons[int(region_final)]) ##cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contours(all_found_texline_polygons[int(region_final)])
###print(all_box_coord[j_cont]) ###print(all_box_coord[j_cont])
###print(cx_t) ###print(cx_t)
###print(cy_t) ###print(cy_t)
@ -292,9 +292,9 @@ def adhere_drop_capital_region_into_corresponding_textline(
region_final = region_with_intersected_drop[np.argmax(sum_pixels_of_intersection)] - 1 region_final = region_with_intersected_drop[np.argmax(sum_pixels_of_intersection)] - 1
# print(region_final,'region_final') # print(region_final,'region_final')
# cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contoures(all_found_texline_polygons[int(region_final)]) # cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contours(all_found_texline_polygons[int(region_final)])
try: try:
cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contoures(all_found_texline_polygons[int(region_final)]) cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contours(all_found_texline_polygons[int(region_final)])
# print(all_box_coord[j_cont]) # print(all_box_coord[j_cont])
# print(cx_t) # print(cx_t)
# print(cy_t) # print(cy_t)
@ -346,12 +346,12 @@ def adhere_drop_capital_region_into_corresponding_textline(
# areas_main=np.array([cv2.contourArea(all_found_texline_polygons[int(region_final)][0][j] ) for j in range(len(all_found_texline_polygons[int(region_final)]))]) # areas_main=np.array([cv2.contourArea(all_found_texline_polygons[int(region_final)][0][j] ) for j in range(len(all_found_texline_polygons[int(region_final)]))])
# cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contoures(all_found_texline_polygons[int(region_final)]) # cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contours(all_found_texline_polygons[int(region_final)])
# print(cx_t,'print') # print(cx_t,'print')
try: try:
# print(all_found_texline_polygons[j_cont][0]) # print(all_found_texline_polygons[j_cont][0])
cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contoures(all_found_texline_polygons[int(region_final)]) cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contours(all_found_texline_polygons[int(region_final)])
# print(all_box_coord[j_cont]) # print(all_box_coord[j_cont])
# print(cx_t) # print(cx_t)
# print(cy_t) # print(cy_t)
@ -417,7 +417,7 @@ def adhere_drop_capital_region_into_corresponding_textline(
#####try: #####try:
#####if len(contours_new_parent)==1: #####if len(contours_new_parent)==1:
######print(all_found_texline_polygons[j_cont][0]) ######print(all_found_texline_polygons[j_cont][0])
#####cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contoures(all_found_texline_polygons[j_cont]) #####cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contours(all_found_texline_polygons[j_cont])
######print(all_box_coord[j_cont]) ######print(all_box_coord[j_cont])
######print(cx_t) ######print(cx_t)
######print(cy_t) ######print(cy_t)

4
qurator/eynollah/utils/marginals.py
Unescape Escape View File

@ -4,7 +4,7 @@ from scipy.signal import find_peaks
from scipy.ndimage import gaussian_filter1d from scipy.ndimage import gaussian_filter1d
from .contour import find_new_features_of_contoures, return_contours_of_interested_region from .contour import find_new_features_of_contours, return_contours_of_interested_region
from .resize import resize_image from .resize import resize_image
from .rotate import rotate_image from .rotate import rotate_image
@ -185,7 +185,7 @@ def get_marginals(text_with_lines, text_regions, num_col, slope_deskew, kernel=N
min_area_text=0.00001 min_area_text=0.00001
polygons_of_marginals=return_contours_of_interested_region(text_regions,pixel_img,min_area_text) polygons_of_marginals=return_contours_of_interested_region(text_regions,pixel_img,min_area_text)
cx_text_only,cy_text_only ,x_min_text_only,x_max_text_only, y_min_text_only ,y_max_text_only,y_cor_x_min_main=find_new_features_of_contoures(polygons_of_marginals) cx_text_only,cy_text_only ,x_min_text_only,x_max_text_only, y_min_text_only ,y_max_text_only,y_cor_x_min_main=find_new_features_of_contours(polygons_of_marginals)
text_regions[(text_regions[:,:]==4)]=1 text_regions[(text_regions[:,:]==4)]=1

Write Preview
Loading…
Cancel
Save