move all plotting code to EynollahPlotter

pull/19/head
Konstantin Baierer 3 years ago
parent 853fd12e40
commit c2e9ebb366

@ -4,13 +4,18 @@ from sbb_newspapers_org_image.eynollah import eynollah
@click.command()
@click.option(
"--image", "-i", help="image filename", type=click.Path(exists=True, dir_okay=False)
"--image",
"-i",
help="image filename",
type=click.Path(exists=True, dir_okay=False),
required=True,
)
@click.option(
"--out",
"-o",
help="directory to write output xml data",
type=click.Path(exists=True, file_okay=False),
required=True,
)
@click.option(
"--model",
@ -42,6 +47,12 @@ from sbb_newspapers_org_image.eynollah import eynollah
help="if a directory is given, all plots needed for documentation will be saved there",
type=click.Path(exists=True, file_okay=False),
)
@click.option(
"--enable_plotting",
"-ep",
is_flag=True,
help="If set, will plot intermediary files and images",
)
@click.option(
"--allow_enhancement",
"-ae",
@ -80,6 +91,7 @@ def main(
save_layout,
save_deskewed,
save_all,
enable_plotting,
allow_enhancement,
curved_line,
full_layout,
@ -95,6 +107,7 @@ def main(
save_layout,
save_deskewed,
save_all,
enable_plotting,
allow_enhancement,
curved_line,
full_layout,

@ -12,11 +12,9 @@ import time
import warnings
from pathlib import Path
from multiprocessing import Process, Queue, cpu_count
from sys import getsizeof
import cv2
import numpy as np
import matplotlib.pyplot as plt
os.environ["TF_CPP_MIN_LOG_LEVEL"] = "3"
stderr = sys.stderr
@ -117,10 +115,10 @@ from .utils import (
from .utils.xml import create_page_xml
from .plot import EynollahPlotter
SLOPE_THRESHOLD = 0.13
class eynollah:
def __init__(
self,
@ -132,6 +130,7 @@ class eynollah:
dir_of_layout=None,
dir_of_deskewed=None,
dir_of_all=None,
enable_plotting=False,
allow_enhancement=False,
curved_line=False,
full_layout=False,
@ -142,17 +141,21 @@ class eynollah:
self.cont_page = []
self.dir_out = dir_out
self.image_filename_stem = image_filename_stem
self.dir_of_cropped_images = dir_of_cropped_images
self.allow_enhancement = allow_enhancement
self.curved_line = curved_line
self.full_layout = full_layout
self.allow_scaling = allow_scaling
self.dir_of_layout = dir_of_layout
self.headers_off = headers_off
self.dir_of_deskewed = dir_of_deskewed
self.dir_of_all = dir_of_all
if not self.image_filename_stem:
self.image_filename_stem = Path(Path(image_filename).name).stem
self.plotter = None if not enable_plotting else EynollahPlotter(
dir_of_all=dir_of_all,
dir_of_deskewed=dir_of_deskewed,
dir_of_cropped_images=dir_of_cropped_images,
dir_of_layout=dir_of_layout,
image_filename=image_filename,
image_filename_stem=image_filename_stem,
)
self.dir_models = dir_models
self.kernel = np.ones((5, 5), np.uint8)
@ -448,8 +451,12 @@ class eynollah:
self.scale_x = self.img_width_int / float(self.image.shape[1])
self.image = resize_image(self.image, self.img_hight_int, self.img_width_int)
del img_res
del img_org
# Also set for the plotter
# XXX TODO hacky
self.plotter.image_org = self.image_org
self.plotter.scale_y = self.scale_y
self.plotter.scale_x = self.scale_x
def get_image_and_scales_after_enhancing(self, img_org, img_res):
@ -922,7 +929,7 @@ class eynollah:
sigma_des = max(1, int(y_diff_mean * (4.0 / 40.0)))
img_int_p[img_int_p > 0] = 1
slope_for_all = return_deskew_slop(img_int_p, sigma_des, dir_of_all=self.dir_of_all, image_filename_stem=self.image_filename_stem)
slope_for_all = return_deskew_slop(img_int_p, sigma_des, plotter=self.plotter)
if abs(slope_for_all) < 0.5:
slope_for_all = [slope_deskew][0]
@ -950,7 +957,7 @@ class eynollah:
textline_biggest_region = mask_biggest * textline_mask_tot_ea
# print(slope_for_all,'slope_for_all')
textline_rotated_seperated = seperate_lines_new2(textline_biggest_region[y : y + h, x : x + w], 0, num_col, slope_for_all, self.dir_of_all, self.image_filename_stem)
textline_rotated_seperated = seperate_lines_new2(textline_biggest_region[y : y + h, x : x + w], 0, num_col, slope_for_all, plotter=self.plotter)
# new line added
##print(np.shape(textline_rotated_seperated),np.shape(mask_biggest))
@ -1036,7 +1043,7 @@ class eynollah:
if sigma_des < 1:
sigma_des = 1
img_int_p[img_int_p > 0] = 1
slope_for_all = return_deskew_slop(img_int_p, sigma_des, dir_of_all=self.dir_of_all, image_filename_stem=self.image_filename_stem)
slope_for_all = return_deskew_slop(img_int_p, sigma_des, plotter=self.plotter)
if abs(slope_for_all) <= 0.5:
slope_for_all = [slope_deskew][0]
except:
@ -1127,7 +1134,7 @@ class eynollah:
sigma_des = 1
crop_img[crop_img > 0] = 1
slope_corresponding_textregion = return_deskew_slop(crop_img, sigma_des, dir_of_all=self.dir_of_all, image_filename_stem=self.image_filename_stem)
slope_corresponding_textregion = return_deskew_slop(crop_img, sigma_des, plotter=self.plotter)
except:
slope_corresponding_textregion = 999
@ -1814,20 +1821,6 @@ class eynollah:
return text_regions_p_true
def write_images_into_directory(self, img_contoures, dir_of_cropped_imgs, image_page):
index = 0
for cont_ind in img_contoures:
x, y, w, h = cv2.boundingRect(cont_ind)
box = [x, y, w, h]
croped_page, page_coord = crop_image_inside_box(box, image_page)
croped_page = resize_image(croped_page, int(croped_page.shape[0] / self.scale_y), int(croped_page.shape[1] / self.scale_x))
path = os.path.join(dir_of_cropped_imgs, self.image_filename_stem + "_" + str(index) + ".jpg")
cv2.imwrite(path, croped_page)
index += 1
def do_order_of_regions(self, contours_only_text_parent, contours_only_text_parent_h, boxes, textline_mask_tot):
if self.full_layout:
@ -2110,88 +2103,6 @@ class eynollah:
return order_text_new, id_of_texts_tot
def save_plot_of_layout_main(self, text_regions_p, image_page):
values = np.unique(text_regions_p[:, :])
# pixels=['Background' , 'Main text' , 'Heading' , 'Marginalia' ,'Drop capitals' , 'Images' , 'Seperators' , 'Tables', 'Graphics']
pixels=['Background' , 'Main text' , 'Image' , 'Separator','Marginalia']
values_indexes = [0, 1, 2, 3, 4]
plt.figure(figsize=(40, 40))
plt.rcParams["font.size"] = "40"
im = plt.imshow(text_regions_p[:, :])
colors = [im.cmap(im.norm(value)) for value in values]
patches = [mpatches.Patch(color=colors[np.where(values == i)[0][0]], label="{l}".format(l=pixels[int(np.where(values_indexes == i)[0][0])])) for i in values]
plt.legend(handles=patches, bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0.0, fontsize=40)
plt.savefig(os.path.join(self.dir_of_layout, self.image_filename_stem + "_layout_main.png"))
def save_plot_of_layout_main_all(self, text_regions_p, image_page):
values = np.unique(text_regions_p[:, :])
# pixels=['Background' , 'Main text' , 'Heading' , 'Marginalia' ,'Drop capitals' , 'Images' , 'Seperators' , 'Tables', 'Graphics']
pixels=['Background' , 'Main text' , 'Image' , 'Separator','Marginalia']
values_indexes = [0, 1, 2, 3, 4]
plt.figure(figsize=(80, 40))
plt.rcParams["font.size"] = "40"
plt.subplot(1, 2, 1)
plt.imshow(image_page)
plt.subplot(1, 2, 2)
im = plt.imshow(text_regions_p[:, :])
colors = [im.cmap(im.norm(value)) for value in values]
patches = [mpatches.Patch(color=colors[np.where(values == i)[0][0]], label="{l}".format(l=pixels[int(np.where(values_indexes == i)[0][0])])) for i in values]
plt.legend(handles=patches, bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0.0, fontsize=60)
plt.savefig(os.path.join(self.dir_of_all, self.image_filename_stem + "_layout_main_and_page.png"))
def save_plot_of_layout(self, text_regions_p, image_page):
values = np.unique(text_regions_p[:, :])
# pixels=['Background' , 'Main text' , 'Heading' , 'Marginalia' ,'Drop capitals' , 'Images' , 'Seperators' , 'Tables', 'Graphics']
pixels = ["Background", "Main text", "Header", "Marginalia", "Drop capital", "Image", "Separator"]
values_indexes = [0, 1, 2, 8, 4, 5, 6]
plt.figure(figsize=(40, 40))
plt.rcParams["font.size"] = "40"
im = plt.imshow(text_regions_p[:, :])
colors = [im.cmap(im.norm(value)) for value in values]
patches = [mpatches.Patch(color=colors[np.where(values == i)[0][0]], label="{l}".format(l=pixels[int(np.where(values_indexes == i)[0][0])])) for i in values]
plt.legend(handles=patches, bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0.0, fontsize=40)
plt.savefig(os.path.join(self.dir_of_layout, self.image_filename_stem + "_layout.png"))
def save_plot_of_layout_all(self, text_regions_p, image_page):
values = np.unique(text_regions_p[:, :])
# pixels=['Background' , 'Main text' , 'Heading' , 'Marginalia' ,'Drop capitals' , 'Images' , 'Seperators' , 'Tables', 'Graphics']
pixels = ["Background", "Main text", "Header", "Marginalia", "Drop capital", "Image", "Separator"]
values_indexes = [0, 1, 2, 8, 4, 5, 6]
plt.figure(figsize=(80, 40))
plt.rcParams["font.size"] = "40"
plt.subplot(1, 2, 1)
plt.imshow(image_page)
plt.subplot(1, 2, 2)
im = plt.imshow(text_regions_p[:, :])
colors = [im.cmap(im.norm(value)) for value in values]
patches = [mpatches.Patch(color=colors[np.where(values == i)[0][0]], label="{l}".format(l=pixels[int(np.where(values_indexes == i)[0][0])])) for i in values]
plt.legend(handles=patches, bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0.0, fontsize=60)
plt.savefig(os.path.join(self.dir_of_all, self.image_filename_stem + "_layout_and_page.png"))
def save_plot_of_textlines(self, textline_mask_tot_ea, image_page):
values = np.unique(textline_mask_tot_ea[:, :])
pixels = ["Background", "Textlines"]
values_indexes = [0, 1]
plt.figure(figsize=(80, 40))
plt.rcParams["font.size"] = "40"
plt.subplot(1, 2, 1)
plt.imshow(image_page)
plt.subplot(1, 2, 2)
im = plt.imshow(textline_mask_tot_ea[:, :])
colors = [im.cmap(im.norm(value)) for value in values]
patches = [mpatches.Patch(color=colors[np.where(values == i)[0][0]], label="{l}".format(l=pixels[int(np.where(values_indexes == i)[0][0])])) for i in values]
plt.legend(handles=patches, bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0.0, fontsize=60)
plt.savefig(os.path.join(self.dir_of_all, self.image_filename_stem + "_textline_and_page.png"))
def save_deskewed_image(self, slope_deskew):
img_rotated = rotyate_image_different(self.image_org, slope_deskew)
if self.dir_of_all is not None:
cv2.imwrite(os.path.join(self.dir_of_all, self.image_filename_stem + "_org.png"), self.image_org)
cv2.imwrite(os.path.join(self.dir_of_deskewed, self.image_filename_stem + "_deskewed.png"), img_rotated)
del img_rotated
def run(self):
is_image_enhanced = False
# get image and sclaes, then extract the page of scanned image
@ -2243,8 +2154,8 @@ class eynollah:
image_page, page_coord = self.extract_page()
# print(image_page.shape,'page')
if self.dir_of_all is not None:
cv2.imwrite(os.path.join(self.dir_of_all, self.image_filename_stem + "_page.png"), image_page)
if self.plotter:
self.plotter.save_page_image(image_page)
K.clear_session()
gc.collect()
@ -2298,8 +2209,8 @@ class eynollah:
K.clear_session()
gc.collect()
#print(np.unique(textline_mask_tot_ea[:, :]), "textline")
if self.dir_of_all is not None:
self.save_plot_of_textlines(textline_mask_tot_ea, image_page)
if self.plotter:
self.plotter.save_plot_of_textlines(textline_mask_tot_ea, image_page)
print("textline: " + str(time.time() - t1))
# plt.imshow(textline_mask_tot_ea)
# plt.show()
@ -2307,11 +2218,11 @@ class eynollah:
sigma = 2
main_page_deskew = True
slope_deskew = return_deskew_slop(cv2.erode(textline_mask_tot_ea, self.kernel, iterations=2), sigma, main_page_deskew, dir_of_all=self.dir_of_all, image_filename_stem=self.image_filename_stem)
slope_first = 0 # return_deskew_slop(cv2.erode(textline_mask_tot_ea, self.kernel, iterations=2),sigma, dir_of_all=self.dir_of_all, image_filename_stem=self.image_filename_stem)
slope_deskew = return_deskew_slop(cv2.erode(textline_mask_tot_ea, self.kernel, iterations=2), sigma, main_page_deskew, plotter=self.plotter)
slope_first = 0 # return_deskew_slop(cv2.erode(textline_mask_tot_ea, self.kernel, iterations=2),sigma, plotter=self.plotter)
if self.dir_of_deskewed is not None:
self.save_deskewed_image(slope_deskew)
if self.plotter:
self.plotter.save_deskewed_image(slope_deskew)
# img_rotated=rotyate_image_different(self.image_org,slope_deskew)
print(slope_deskew, "slope_deskew")
@ -2344,10 +2255,9 @@ class eynollah:
# plt.imshow(text_regions_p)
# plt.show()
if self.dir_of_all is not None:
self.save_plot_of_layout_main_all(text_regions_p, image_page)
if self.dir_of_layout is not None:
self.save_plot_of_layout_main(text_regions_p, image_page)
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)
print("marginals: " + str(time.time() - t1))
@ -2632,10 +2542,9 @@ class eynollah:
contours_only_text_parent_d_ordered = None
text_regions_p, contours_only_text_parent, contours_only_text_parent_h, all_box_coord, all_box_coord_h, all_found_texline_polygons, all_found_texline_polygons_h, slopes, slopes_h, contours_only_text_parent_d_ordered, contours_only_text_parent_h_d_ordered = check_any_text_region_in_model_one_is_main_or_header(text_regions_p, regions_fully, contours_only_text_parent, all_box_coord, all_found_texline_polygons, slopes, contours_only_text_parent_d_ordered)
if self.dir_of_layout is not None:
self.save_plot_of_layout(text_regions_p, image_page)
if self.dir_of_all is not None:
self.save_plot_of_layout_all(text_regions_p, image_page)
if self.plotter:
self.plotter.save_plot_of_layout(text_regions_p, image_page)
self.plotter.save_plot_of_layout_all(text_regions_p, image_page)
K.clear_session()
gc.collect()
@ -2696,8 +2605,8 @@ class eynollah:
boxes_d = return_boxes_of_images_by_order_of_reading_new(spliter_y_new_d, regions_without_seperators_d, matrix_of_lines_ch_d, num_col_classifier)
# print(slopes)
if self.dir_of_cropped_images is not None:
self.write_images_into_directory(polygons_of_images, self.dir_of_cropped_images, image_page)
if self.plotter:
self.plotter.write_images_into_directory(polygons_of_images, image_page)
if self.full_layout:
if np.abs(slope_deskew) < SLOPE_THRESHOLD:

@ -0,0 +1,159 @@
import matplotlib.pyplot as plt
import matplotlib.patches as mpatches
import numpy as np
import os.path
import cv2
from scipy.ndimage import gaussian_filter1d
from .utils import crop_image_inside_box
from .utils.rotate import rotyate_image_different
from .utils.resize import resize_image
class EynollahPlotter():
"""
Class collecting all the plotting and image writing methods
"""
def __init__(
self,
*,
dir_of_all,
dir_of_deskewed,
dir_of_layout,
dir_of_cropped_images,
image_filename,
image_filename_stem,
image_org=None,
scale_x=1,
scale_y=1,
):
self.dir_of_all = dir_of_all
self.dir_of_layout = dir_of_layout
self.dir_of_cropped_images = dir_of_cropped_images
self.dir_of_deskewed = dir_of_deskewed
self.image_filename = image_filename
self.image_filename_stem = image_filename_stem
# XXX TODO hacky these cannot be set at init time
self.image_org = image_org
self.scale_x = scale_x
self.scale_y = scale_y
def save_plot_of_layout_main(self, text_regions_p, image_page):
values = np.unique(text_regions_p[:, :])
# pixels=['Background' , 'Main text' , 'Heading' , 'Marginalia' ,'Drop capitals' , 'Images' , 'Seperators' , 'Tables', 'Graphics']
pixels=['Background' , 'Main text' , 'Image' , 'Separator','Marginalia']
values_indexes = [0, 1, 2, 3, 4]
plt.figure(figsize=(40, 40))
plt.rcParams["font.size"] = "40"
im = plt.imshow(text_regions_p[:, :])
colors = [im.cmap(im.norm(value)) for value in values]
patches = [mpatches.Patch(color=colors[np.where(values == i)[0][0]], label="{l}".format(l=pixels[int(np.where(values_indexes == i)[0][0])])) for i in values]
plt.legend(handles=patches, bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0.0, fontsize=40)
plt.savefig(os.path.join(self.dir_of_layout, self.image_filename_stem + "_layout_main.png"))
def save_plot_of_layout_main_all(self, text_regions_p, image_page):
values = np.unique(text_regions_p[:, :])
# pixels=['Background' , 'Main text' , 'Heading' , 'Marginalia' ,'Drop capitals' , 'Images' , 'Seperators' , 'Tables', 'Graphics']
pixels=['Background' , 'Main text' , 'Image' , 'Separator','Marginalia']
values_indexes = [0, 1, 2, 3, 4]
plt.figure(figsize=(80, 40))
plt.rcParams["font.size"] = "40"
plt.subplot(1, 2, 1)
plt.imshow(image_page)
plt.subplot(1, 2, 2)
im = plt.imshow(text_regions_p[:, :])
colors = [im.cmap(im.norm(value)) for value in values]
patches = [mpatches.Patch(color=colors[np.where(values == i)[0][0]], label="{l}".format(l=pixels[int(np.where(values_indexes == i)[0][0])])) for i in values]
plt.legend(handles=patches, bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0.0, fontsize=60)
plt.savefig(os.path.join(self.dir_of_all, self.image_filename_stem + "_layout_main_and_page.png"))
def save_plot_of_layout(self, text_regions_p, image_page):
values = np.unique(text_regions_p[:, :])
# pixels=['Background' , 'Main text' , 'Heading' , 'Marginalia' ,'Drop capitals' , 'Images' , 'Seperators' , 'Tables', 'Graphics']
pixels = ["Background", "Main text", "Header", "Marginalia", "Drop capital", "Image", "Separator"]
values_indexes = [0, 1, 2, 8, 4, 5, 6]
plt.figure(figsize=(40, 40))
plt.rcParams["font.size"] = "40"
im = plt.imshow(text_regions_p[:, :])
colors = [im.cmap(im.norm(value)) for value in values]
patches = [mpatches.Patch(color=colors[np.where(values == i)[0][0]], label="{l}".format(l=pixels[int(np.where(values_indexes == i)[0][0])])) for i in values]
plt.legend(handles=patches, bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0.0, fontsize=40)
plt.savefig(os.path.join(self.dir_of_layout, self.image_filename_stem + "_layout.png"))
def save_plot_of_layout_all(self, text_regions_p, image_page):
values = np.unique(text_regions_p[:, :])
# pixels=['Background' , 'Main text' , 'Heading' , 'Marginalia' ,'Drop capitals' , 'Images' , 'Seperators' , 'Tables', 'Graphics']
pixels = ["Background", "Main text", "Header", "Marginalia", "Drop capital", "Image", "Separator"]
values_indexes = [0, 1, 2, 8, 4, 5, 6]
plt.figure(figsize=(80, 40))
plt.rcParams["font.size"] = "40"
plt.subplot(1, 2, 1)
plt.imshow(image_page)
plt.subplot(1, 2, 2)
im = plt.imshow(text_regions_p[:, :])
colors = [im.cmap(im.norm(value)) for value in values]
patches = [mpatches.Patch(color=colors[np.where(values == i)[0][0]], label="{l}".format(l=pixels[int(np.where(values_indexes == i)[0][0])])) for i in values]
plt.legend(handles=patches, bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0.0, fontsize=60)
plt.savefig(os.path.join(self.dir_of_all, self.image_filename_stem + "_layout_and_page.png"))
def save_plot_of_textlines(self, textline_mask_tot_ea, image_page):
values = np.unique(textline_mask_tot_ea[:, :])
pixels = ["Background", "Textlines"]
values_indexes = [0, 1]
plt.figure(figsize=(80, 40))
plt.rcParams["font.size"] = "40"
plt.subplot(1, 2, 1)
plt.imshow(image_page)
plt.subplot(1, 2, 2)
im = plt.imshow(textline_mask_tot_ea[:, :])
colors = [im.cmap(im.norm(value)) for value in values]
patches = [mpatches.Patch(color=colors[np.where(values == i)[0][0]], label="{l}".format(l=pixels[int(np.where(values_indexes == i)[0][0])])) for i in values]
plt.legend(handles=patches, bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0.0, fontsize=60)
plt.savefig(os.path.join(self.dir_of_all, self.image_filename_stem + "_textline_and_page.png"))
def save_deskewed_image(self, slope_deskew):
if self.dir_of_all is not None:
img_rotated = rotyate_image_different(self.image_org, slope_deskew)
cv2.imwrite(os.path.join(self.dir_of_all, self.image_filename_stem + "_org.png"), self.image_org)
cv2.imwrite(os.path.join(self.dir_of_deskewed, self.image_filename_stem + "_deskewed.png"), img_rotated)
def save_page_image(self, image_page):
cv2.imwrite(os.path.join(self.dir_of_all, self.image_filename_stem + "_page.png"), image_page)
def save_plot_of_textline_density(self, img_patch_org):
plt.figure(figsize=(80,40))
plt.rcParams['font.size']='50'
plt.subplot(1,2,1)
plt.imshow(img_patch_org)
plt.subplot(1,2,2)
plt.plot(gaussian_filter1d(img_patch_org.sum(axis=1), 3),np.array(range(len(gaussian_filter1d(img_patch_org.sum(axis=1), 3)))),linewidth=8)
plt.xlabel('Density of textline prediction in direction of X axis',fontsize=60)
plt.ylabel('Height',fontsize=60)
plt.yticks([0,len(gaussian_filter1d(img_patch_org.sum(axis=1), 3))])
plt.gca().invert_yaxis()
plt.savefig(os.path.join(self.dir_of_all, self.image_filename_stem+'_density_of_textline.png'))
def save_plot_of_rotation_angle(self, angels, var_res):
#print('galdi?')
plt.figure(figsize=(60,30))
plt.rcParams['font.size']='50'
plt.plot(angels,np.array(var_res),'-o',markersize=25,linewidth=4)
plt.xlabel('angle',fontsize=50)
plt.ylabel('variance of sum of rotated textline in direction of x axis',fontsize=50)
plt.plot(angels[np.argmax(var_res)],var_res[np.argmax(np.array(var_res))] ,'*',markersize=50,label='Angle of deskewing=' +str("{:.2f}".format(angels[np.argmax(var_res)]))+r'$\degree$')
plt.legend(loc='best')
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):
index = 0
for cont_ind in img_contoures:
x, y, w, h = cv2.boundingRect(cont_ind)
box = [x, y, w, h]
croped_page, page_coord = crop_image_inside_box(box, image_page)
croped_page = resize_image(croped_page, int(croped_page.shape[0] / self.scale_y), int(croped_page.shape[1] / self.scale_x))
path = os.path.join(self.dir_of_cropped_images, self.image_filename_stem + "_" + str(index) + ".jpg")
cv2.imwrite(path, croped_page)
index += 1

@ -372,108 +372,9 @@ def boosting_headers_by_longshot_region_segmentation(textregion_pre_p, textregio
def find_num_col_deskew(regions_without_seperators, sigma_, multiplier=3.8):
regions_without_seperators_0=regions_without_seperators[:,:].sum(axis=1)
##meda_n_updown=regions_without_seperators_0[len(regions_without_seperators_0)::-1]
##first_nonzero=(next((i for i, x in enumerate(regions_without_seperators_0) if x), 0))
##last_nonzero=(next((i for i, x in enumerate(meda_n_updown) if x), 0))
##last_nonzero=len(regions_without_seperators_0)-last_nonzero
y=regions_without_seperators_0#[first_nonzero:last_nonzero]
##y_help=np.zeros(len(y)+20)
##y_help[10:len(y)+10]=y
##x=np.array( range(len(y)) )
##zneg_rev=-y_help+np.max(y_help)
##zneg=np.zeros(len(zneg_rev)+20)
##zneg[10:len(zneg_rev)+10]=zneg_rev
z=gaussian_filter1d(y, sigma_)
###zneg= gaussian_filter1d(zneg, sigma_)
###peaks_neg, _ = find_peaks(zneg, height=0)
###peaks, _ = find_peaks(z, height=0)
###peaks_neg=peaks_neg-10-10
####print(np.std(z),'np.std(z)np.std(z)np.std(z)')
#####plt.plot(z)
#####plt.show()
#####plt.imshow(regions_without_seperators)
#####plt.show()
###"""
###last_nonzero=last_nonzero-0#100
###first_nonzero=first_nonzero+0#+100
###peaks_neg=peaks_neg[(peaks_neg>first_nonzero) & (peaks_neg<last_nonzero)]
###peaks=peaks[(peaks>.06*regions_without_seperators.shape[1]) & (peaks<0.94*regions_without_seperators.shape[1])]
###"""
###interest_pos=z[peaks]
###interest_pos=interest_pos[interest_pos>10]
###interest_neg=z[peaks_neg]
###min_peaks_pos=np.mean(interest_pos)
###min_peaks_neg=0#np.min(interest_neg)
###dis_talaei=(min_peaks_pos-min_peaks_neg)/multiplier
####print(interest_pos)
###grenze=min_peaks_pos-dis_talaei#np.mean(y[peaks_neg[0]:peaks_neg[len(peaks_neg)-1]])-np.std(y[peaks_neg[0]:peaks_neg[len(peaks_neg)-1]])/2.0
###interest_neg_fin=interest_neg[(interest_neg<grenze)]
###peaks_neg_fin=peaks_neg[(interest_neg<grenze)]
###interest_neg_fin=interest_neg[(interest_neg<grenze)]
###"""
###if interest_neg[0]<0.1:
###interest_neg=interest_neg[1:]
###if interest_neg[len(interest_neg)-1]<0.1:
###interest_neg=interest_neg[:len(interest_neg)-1]
###min_peaks_pos=np.min(interest_pos)
###min_peaks_neg=0#np.min(interest_neg)
###dis_talaei=(min_peaks_pos-min_peaks_neg)/multiplier
###grenze=min_peaks_pos-dis_talaei#np.mean(y[peaks_neg[0]:peaks_neg[len(peaks_neg)-1]])-np.std(y[peaks_neg[0]:peaks_neg[len(peaks_neg)-1]])/2.0
###"""
####interest_neg_fin=interest_neg#[(interest_neg<grenze)]
####peaks_neg_fin=peaks_neg#[(interest_neg<grenze)]
####interest_neg_fin=interest_neg#[(interest_neg<grenze)]
###num_col=(len(interest_neg_fin))+1
###p_l=0
###p_u=len(y)-1
###p_m=int(len(y)/2.)
###p_g_l=int(len(y)/3.)
###p_g_u=len(y)-int(len(y)/3.)
###diff_peaks=np.abs( np.diff(peaks_neg_fin) )
###diff_peaks_annormal=diff_peaks[diff_peaks<30]
#print(len(interest_neg_fin),np.mean(interest_neg_fin))
return np.std(z)#interest_neg_fin,np.std(z)
regions_without_seperators_0 = regions_without_seperators[:,:].sum(axis=1)
z = gaussian_filter1d(regions_without_seperators_0, sigma_)
return np.std(z)
def return_hor_spliter_by_index_for_without_verticals(peaks_neg_fin_t, x_min_hor_some, x_max_hor_some):
# print(peaks_neg_fin_t,x_min_hor_some,x_max_hor_some)

@ -1,4 +1,3 @@
import matplotlib.pyplot as plt
import numpy as np
import cv2
from scipy.signal import find_peaks
@ -1485,7 +1484,7 @@ def textline_contours_postprocessing(textline_mask, slope, contour_text_interest
return contours_rotated_clean
def seperate_lines_new2(img_path, thetha, num_col, slope_region, dir_of_all, image_filename_stem):
def seperate_lines_new2(img_path, thetha, num_col, slope_region, plotter=None):
if num_col == 1:
num_patches = int(img_path.shape[1] / 200.0)
@ -1536,7 +1535,7 @@ def seperate_lines_new2(img_path, thetha, num_col, slope_region, dir_of_all, ima
sigma = 2
try:
slope_xline = return_deskew_slop(img_xline, sigma, dir_of_all=dir_of_all, image_filename_stem=image_filename_stem)
slope_xline = return_deskew_slop(img_xline, sigma, plotter=plotter)
except:
slope_xline = 0
@ -1593,29 +1592,10 @@ def seperate_lines_new2(img_path, thetha, num_col, slope_region, dir_of_all, ima
# plt.show()
return img_patch_ineterst_revised
def return_deskew_slop(img_patch_org, sigma_des, main_page=False, dir_of_all=None, image_filename_stem=None):
def return_deskew_slop(img_patch_org, sigma_des, main_page=False, plotter=None):
if main_page and dir_of_all is not None:
plt.figure(figsize=(80,40))
plt.rcParams['font.size']='50'
plt.subplot(1,2,1)
plt.imshow(img_patch_org)
plt.subplot(1,2,2)
plt.plot(gaussian_filter1d(img_patch_org.sum(axis=1), 3),np.array(range(len(gaussian_filter1d(img_patch_org.sum(axis=1), 3)))),linewidth=8)
plt.xlabel('Density of textline prediction in direction of X axis',fontsize=60)
plt.ylabel('Height',fontsize=60)
plt.yticks([0,len(gaussian_filter1d(img_patch_org.sum(axis=1), 3))])
plt.gca().invert_yaxis()
plt.savefig(os.path.join(dir_of_all, image_filename_stem+'_density_of_textline.png'))
#print(np.max(img_patch_org.sum(axis=0)) ,np.max(img_patch_org.sum(axis=1)),'axislar')
#img_patch_org=resize_image(img_patch_org,int(img_patch_org.shape[0]*2.5),int(img_patch_org.shape[1]/2.5))
#print(np.max(img_patch_org.sum(axis=0)) ,np.max(img_patch_org.sum(axis=1)),'axislar2')
if main_page and plotter:
plotter.save_plot_of_textline_density(img_patch_org)
img_int=np.zeros((img_patch_org.shape[0],img_patch_org.shape[1]))
img_int[:,:]=img_patch_org[:,:]#img_patch_org[:,:,0]
@ -1713,17 +1693,8 @@ def return_deskew_slop(img_patch_org, sigma_des, main_page=False, dir_of_all=Non
var_res.append(var_spectrum)
if dir_of_all is not None:
#print('galdi?')
plt.figure(figsize=(60,30))
plt.rcParams['font.size']='50'
plt.plot(angels,np.array(var_res),'-o',markersize=25,linewidth=4)
plt.xlabel('angle',fontsize=50)
plt.ylabel('variance of sum of rotated textline in direction of x axis',fontsize=50)
plt.plot(angels[np.argmax(var_res)],var_res[np.argmax(np.array(var_res))] ,'*',markersize=50,label='Angle of deskewing=' +str("{:.2f}".format(angels[np.argmax(var_res)]))+r'$\degree$')
plt.legend(loc='best')
plt.savefig(os.path.join(dir_of_all,image_filename_stem+'_rotation_angle.png'))
if plotter:
plotter.save_plot_of_rotation_angle(angels, var_res)
try:
var_res=np.array(var_res)
ang_int=angels[np.argmax(var_res)]#angels_sorted[arg_final]#angels[arg_sort_early[arg_sort[arg_final]]]#angels[arg_fin]

Loading…
Cancel
Save