mirror of
https://github.com/qurator-spk/eynollah.git
synced 2025-12-15 15:44:13 +01:00
💀 remove dead code from eynollah.py
This commit is contained in:
kba
parent
1eef5514d7
commit
fcd87fc3cf
4 changed files with 5 additions and 339 deletions
|
|
@ -83,9 +83,7 @@ from .utils.rotate import (
|
|||
from .utils.separate_lines import (
|
||||
separate_lines_new2,
|
||||
return_deskew_slop,
|
||||
do_work_of_slopes_new,
|
||||
do_work_of_slopes_new_curved,
|
||||
do_work_of_slopes_new_light,
|
||||
)
|
||||
from .utils.drop_capitals import (
|
||||
adhere_drop_capital_region_into_corresponding_textline,
|
||||
|
|
@ -96,7 +94,7 @@ from .utils.resize import resize_image
|
|||
from .utils.shm import share_ndarray
|
||||
from .utils import (
|
||||
is_image_filename,
|
||||
boosting_headers_by_longshot_region_segmentation,
|
||||
isNaN,
|
||||
crop_image_inside_box,
|
||||
box2rect,
|
||||
box2slice,
|
||||
|
|
@ -290,9 +288,6 @@ class Eynollah:
|
|||
key += '_uint8'
|
||||
return self._imgs[key].copy()
|
||||
|
||||
def isNaN(self, num):
|
||||
return num != num
|
||||
|
||||
def predict_enhancement(self, img):
|
||||
self.logger.debug("enter predict_enhancement")
|
||||
|
||||
|
|
@ -1637,42 +1632,6 @@ class Eynollah:
|
|||
all_box_coord,
|
||||
slopes)
|
||||
|
||||
def get_slopes_and_deskew_new_light(self, contours, contours_par, textline_mask_tot, boxes, slope_deskew):
|
||||
if not len(contours):
|
||||
return [], [], []
|
||||
self.logger.debug("enter get_slopes_and_deskew_new_light")
|
||||
with share_ndarray(textline_mask_tot) as textline_mask_tot_shared:
|
||||
assert self.executor
|
||||
results = self.executor.map(partial(do_work_of_slopes_new_light,
|
||||
textline_mask_tot_ea=textline_mask_tot_shared,
|
||||
slope_deskew=slope_deskew,
|
||||
textline_light=True,
|
||||
logger=self.logger,),
|
||||
boxes, contours, contours_par)
|
||||
results = list(results) # exhaust prior to release
|
||||
#textline_polygons, box_coord, slopes = zip(*results)
|
||||
self.logger.debug("exit get_slopes_and_deskew_new_light")
|
||||
return tuple(zip(*results))
|
||||
|
||||
def get_slopes_and_deskew_new(self, contours, contours_par, textline_mask_tot, boxes, slope_deskew):
|
||||
if not len(contours):
|
||||
return [], [], []
|
||||
self.logger.debug("enter get_slopes_and_deskew_new")
|
||||
with share_ndarray(textline_mask_tot) as textline_mask_tot_shared:
|
||||
assert self.executor
|
||||
results = self.executor.map(partial(do_work_of_slopes_new,
|
||||
textline_mask_tot_ea=textline_mask_tot_shared,
|
||||
slope_deskew=slope_deskew,
|
||||
MAX_SLOPE=MAX_SLOPE,
|
||||
KERNEL=KERNEL,
|
||||
logger=self.logger,
|
||||
plotter=self.plotter,),
|
||||
boxes, contours, contours_par)
|
||||
results = list(results) # exhaust prior to release
|
||||
#textline_polygons, box_coord, slopes = zip(*results)
|
||||
self.logger.debug("exit get_slopes_and_deskew_new")
|
||||
return tuple(zip(*results))
|
||||
|
||||
def get_slopes_and_deskew_new_curved(self, contours_par, textline_mask_tot, boxes,
|
||||
mask_texts_only, num_col, scale_par, slope_deskew):
|
||||
if not len(contours_par):
|
||||
|
|
@ -1959,145 +1918,6 @@ class Eynollah:
|
|||
img_bin,
|
||||
confidence_matrix)
|
||||
|
||||
def get_regions_from_xy_2models(self,img,is_image_enhanced, num_col_classifier):
|
||||
self.logger.debug("enter get_regions_from_xy_2models")
|
||||
erosion_hurts = False
|
||||
img_org = np.copy(img)
|
||||
img_height_h = img_org.shape[0]
|
||||
img_width_h = img_org.shape[1]
|
||||
|
||||
ratio_y=1.3
|
||||
ratio_x=1
|
||||
|
||||
img = resize_image(img_org, int(img_org.shape[0]*ratio_y), int(img_org.shape[1]*ratio_x))
|
||||
prediction_regions_org_y = self.do_prediction(True, img, self.model_zoo.get("region"))
|
||||
prediction_regions_org_y = resize_image(prediction_regions_org_y, img_height_h, img_width_h )
|
||||
|
||||
#plt.imshow(prediction_regions_org_y[:,:,0])
|
||||
#plt.show()
|
||||
prediction_regions_org_y = prediction_regions_org_y[:,:,0]
|
||||
mask_zeros_y = (prediction_regions_org_y[:,:]==0)*1
|
||||
|
||||
##img_only_regions_with_sep = ( (prediction_regions_org_y[:,:] != 3) & (prediction_regions_org_y[:,:] != 0) )*1
|
||||
img_only_regions_with_sep = (prediction_regions_org_y == 1).astype(np.uint8)
|
||||
try:
|
||||
img_only_regions = cv2.erode(img_only_regions_with_sep[:,:], KERNEL, iterations=20)
|
||||
_, _ = find_num_col(img_only_regions, num_col_classifier, self.tables, multiplier=6.0)
|
||||
img = resize_image(img_org, int(img_org.shape[0]), int(img_org.shape[1]*(1.2 if is_image_enhanced else 1)))
|
||||
|
||||
prediction_regions_org = self.do_prediction(True, img, self.model_zoo.get("region"))
|
||||
prediction_regions_org = resize_image(prediction_regions_org, img_height_h, img_width_h )
|
||||
|
||||
prediction_regions_org=prediction_regions_org[:,:,0]
|
||||
prediction_regions_org[(prediction_regions_org[:,:]==1) & (mask_zeros_y[:,:]==1)]=0
|
||||
|
||||
img = resize_image(img_org, int(img_org.shape[0]), int(img_org.shape[1]))
|
||||
|
||||
prediction_regions_org2 = self.do_prediction(True, img, self.model_zoo.get("region_p2"), marginal_of_patch_percent=0.2)
|
||||
prediction_regions_org2=resize_image(prediction_regions_org2, img_height_h, img_width_h )
|
||||
|
||||
mask_zeros2 = (prediction_regions_org2[:,:,0] == 0)
|
||||
mask_lines2 = (prediction_regions_org2[:,:,0] == 3)
|
||||
text_sume_early = (prediction_regions_org[:,:] == 1).sum()
|
||||
prediction_regions_org_copy = np.copy(prediction_regions_org)
|
||||
prediction_regions_org_copy[(prediction_regions_org_copy[:,:]==1) & (mask_zeros2[:,:]==1)] = 0
|
||||
text_sume_second = ((prediction_regions_org_copy[:,:]==1)*1).sum()
|
||||
rate_two_models = 100. * text_sume_second / text_sume_early
|
||||
|
||||
self.logger.info("ratio_of_two_models: %s", rate_two_models)
|
||||
if not(is_image_enhanced and rate_two_models < RATIO_OF_TWO_MODEL_THRESHOLD):
|
||||
prediction_regions_org = np.copy(prediction_regions_org_copy)
|
||||
|
||||
prediction_regions_org[(mask_lines2[:,:]==1) & (prediction_regions_org[:,:]==0)]=3
|
||||
mask_lines_only=(prediction_regions_org[:,:]==3)*1
|
||||
prediction_regions_org = cv2.erode(prediction_regions_org[:,:], KERNEL, iterations=2)
|
||||
prediction_regions_org = cv2.dilate(prediction_regions_org[:,:], KERNEL, iterations=2)
|
||||
|
||||
if rate_two_models<=40:
|
||||
if self.input_binary:
|
||||
prediction_bin = np.copy(img_org)
|
||||
else:
|
||||
prediction_bin = self.do_prediction(True, img_org, self.model_zoo.get("binarization"), n_batch_inference=5)
|
||||
prediction_bin = resize_image(prediction_bin, img_height_h, img_width_h )
|
||||
prediction_bin = 255 * (prediction_bin[:,:,0]==0)
|
||||
prediction_bin = np.repeat(prediction_bin[:, :, np.newaxis], 3, axis=2)
|
||||
|
||||
ratio_y=1
|
||||
ratio_x=1
|
||||
|
||||
img = resize_image(prediction_bin, int(img_org.shape[0]*ratio_y), int(img_org.shape[1]*ratio_x))
|
||||
|
||||
prediction_regions_org = self.do_prediction(True, img, self.model_zoo.get("region"))
|
||||
prediction_regions_org = resize_image(prediction_regions_org, img_height_h, img_width_h )
|
||||
prediction_regions_org=prediction_regions_org[:,:,0]
|
||||
|
||||
mask_lines_only=(prediction_regions_org[:,:]==3)*1
|
||||
|
||||
mask_texts_only=(prediction_regions_org[:,:]==1)*1
|
||||
mask_images_only=(prediction_regions_org[:,:]==2)*1
|
||||
|
||||
polygons_seplines, hir_seplines = return_contours_of_image(mask_lines_only)
|
||||
polygons_seplines = filter_contours_area_of_image(
|
||||
mask_lines_only, polygons_seplines, hir_seplines, max_area=1, min_area=0.00001, dilate=1)
|
||||
|
||||
polygons_of_only_texts = return_contours_of_interested_region(mask_texts_only, 1, 0.00001)
|
||||
polygons_of_only_lines = return_contours_of_interested_region(mask_lines_only, 1, 0.00001)
|
||||
|
||||
text_regions_p_true = np.zeros(prediction_regions_org.shape)
|
||||
text_regions_p_true = cv2.fillPoly(text_regions_p_true,pts = polygons_of_only_lines, color=(3, 3, 3))
|
||||
text_regions_p_true[:,:][mask_images_only[:,:] == 1] = 2
|
||||
|
||||
text_regions_p_true=cv2.fillPoly(text_regions_p_true,pts=polygons_of_only_texts, color=(1,1,1))
|
||||
|
||||
self.logger.debug("exit get_regions_from_xy_2models")
|
||||
return text_regions_p_true, erosion_hurts, polygons_seplines, polygons_of_only_texts
|
||||
except:
|
||||
if self.input_binary:
|
||||
prediction_bin = np.copy(img_org)
|
||||
prediction_bin = self.do_prediction(True, img_org, self.model_zoo.get("binarization"), n_batch_inference=5)
|
||||
prediction_bin = resize_image(prediction_bin, img_height_h, img_width_h )
|
||||
prediction_bin = 255 * (prediction_bin[:,:,0]==0)
|
||||
prediction_bin = np.repeat(prediction_bin[:, :, np.newaxis], 3, axis=2)
|
||||
else:
|
||||
prediction_bin = np.copy(img_org)
|
||||
ratio_y=1
|
||||
ratio_x=1
|
||||
|
||||
|
||||
img = resize_image(prediction_bin, int(img_org.shape[0]*ratio_y), int(img_org.shape[1]*ratio_x))
|
||||
prediction_regions_org = self.do_prediction(True, img, self.model_zoo.get("region"))
|
||||
prediction_regions_org = resize_image(prediction_regions_org, img_height_h, img_width_h )
|
||||
prediction_regions_org=prediction_regions_org[:,:,0]
|
||||
|
||||
#mask_lines_only=(prediction_regions_org[:,:]==3)*1
|
||||
#img = resize_image(img_org, int(img_org.shape[0]*1), int(img_org.shape[1]*1))
|
||||
|
||||
#prediction_regions_org = self.do_prediction(True, img, self.model_zoo.get_model("region"))
|
||||
#prediction_regions_org = resize_image(prediction_regions_org, img_height_h, img_width_h )
|
||||
#prediction_regions_org = prediction_regions_org[:,:,0]
|
||||
#prediction_regions_org[(prediction_regions_org[:,:] == 1) & (mask_zeros_y[:,:] == 1)]=0
|
||||
|
||||
mask_lines_only = (prediction_regions_org == 3)*1
|
||||
mask_texts_only = (prediction_regions_org == 1)*1
|
||||
mask_images_only= (prediction_regions_org == 2)*1
|
||||
|
||||
polygons_seplines, hir_seplines = return_contours_of_image(mask_lines_only)
|
||||
polygons_seplines = filter_contours_area_of_image(
|
||||
mask_lines_only, polygons_seplines, hir_seplines, max_area=1, min_area=0.00001, dilate=1)
|
||||
|
||||
polygons_of_only_texts = return_contours_of_interested_region(mask_texts_only,1,0.00001)
|
||||
polygons_of_only_lines = return_contours_of_interested_region(mask_lines_only,1,0.00001)
|
||||
|
||||
text_regions_p_true = np.zeros(prediction_regions_org.shape)
|
||||
text_regions_p_true = cv2.fillPoly(text_regions_p_true, pts = polygons_of_only_lines, color=(3,3,3))
|
||||
|
||||
text_regions_p_true[:,:][mask_images_only[:,:] == 1] = 2
|
||||
text_regions_p_true = cv2.fillPoly(text_regions_p_true, pts = polygons_of_only_texts, color=(1,1,1))
|
||||
|
||||
erosion_hurts = True
|
||||
self.logger.debug("exit get_regions_from_xy_2models")
|
||||
return text_regions_p_true, erosion_hurts, polygons_seplines, polygons_of_only_texts
|
||||
|
||||
def do_order_of_regions(
|
||||
self, contours_only_text_parent, contours_only_text_parent_h, boxes, textline_mask_tot):
|
||||
|
||||
|
|
@ -2343,7 +2163,7 @@ class Eynollah:
|
|||
|
||||
img_comm = cv2.fillPoly(img_comm, pts=main_contours, color=indiv)
|
||||
|
||||
if not self.isNaN(slope_mean_hor):
|
||||
if not isNaN(slope_mean_hor):
|
||||
image_revised_last = np.zeros(image_regions_eraly_p.shape[:2])
|
||||
for i in range(len(boxes)):
|
||||
box_ys = slice(*boxes[i][2:4])
|
||||
|
|
@ -2622,52 +2442,6 @@ class Eynollah:
|
|||
|
||||
return page_coord, image_page, textline_mask_tot_ea, img_bin_light, cont_page
|
||||
|
||||
def run_graphics_and_columns(
|
||||
self, text_regions_p_1,
|
||||
num_col_classifier, num_column_is_classified, erosion_hurts):
|
||||
|
||||
t_in_gr = time.time()
|
||||
img_g = self.imread(grayscale=True, uint8=True)
|
||||
|
||||
img_g3 = np.zeros((img_g.shape[0], img_g.shape[1], 3))
|
||||
img_g3 = img_g3.astype(np.uint8)
|
||||
img_g3[:, :, 0] = img_g[:, :]
|
||||
img_g3[:, :, 1] = img_g[:, :]
|
||||
img_g3[:, :, 2] = img_g[:, :]
|
||||
|
||||
image_page, page_coord, cont_page = self.extract_page()
|
||||
|
||||
if self.tables:
|
||||
table_prediction = self.get_tables_from_model(image_page, num_col_classifier)
|
||||
else:
|
||||
table_prediction = np.zeros((image_page.shape[0], image_page.shape[1])).astype(np.int16)
|
||||
|
||||
if self.plotter:
|
||||
self.plotter.save_page_image(image_page)
|
||||
|
||||
text_regions_p_1 = text_regions_p_1[page_coord[0] : page_coord[1], page_coord[2] : page_coord[3]]
|
||||
mask_images = (text_regions_p_1[:, :] == 2) * 1
|
||||
mask_images = mask_images.astype(np.uint8)
|
||||
mask_images = cv2.erode(mask_images[:, :], KERNEL, iterations=10)
|
||||
mask_lines = (text_regions_p_1[:, :] == 3) * 1
|
||||
mask_lines = mask_lines.astype(np.uint8)
|
||||
img_only_regions_with_sep = ((text_regions_p_1[:, :] != 3) & (text_regions_p_1[:, :] != 0)) * 1
|
||||
img_only_regions_with_sep = img_only_regions_with_sep.astype(np.uint8)
|
||||
|
||||
if erosion_hurts:
|
||||
img_only_regions = np.copy(img_only_regions_with_sep[:,:])
|
||||
else:
|
||||
img_only_regions = cv2.erode(img_only_regions_with_sep[:,:], KERNEL, iterations=6)
|
||||
try:
|
||||
num_col, _ = find_num_col(img_only_regions, num_col_classifier, self.tables, multiplier=6.0)
|
||||
num_col = num_col + 1
|
||||
if not num_column_is_classified:
|
||||
num_col_classifier = num_col + 1
|
||||
except Exception as why:
|
||||
self.logger.error(why)
|
||||
num_col = None
|
||||
return (num_col, num_col_classifier, img_only_regions, page_coord, image_page, mask_images, mask_lines,
|
||||
text_regions_p_1, cont_page, table_prediction)
|
||||
|
||||
def run_enhancement(self, light_version):
|
||||
t_in = time.time()
|
||||
|
|
@ -2685,10 +2459,7 @@ class Eynollah:
|
|||
else:
|
||||
self.get_image_and_scales_after_enhancing(img_org, img_res)
|
||||
else:
|
||||
if self.allow_enhancement:
|
||||
self.get_image_and_scales(img_org, img_res, scale)
|
||||
else:
|
||||
self.get_image_and_scales(img_org, img_res, scale)
|
||||
self.get_image_and_scales(img_org, img_res, scale)
|
||||
if self.allow_scaling:
|
||||
img_org, img_res, is_image_enhanced = \
|
||||
self.resize_image_with_column_classifier(is_image_enhanced, img_bin)
|
||||
|
|
@ -3341,42 +3112,6 @@ class Eynollah:
|
|||
region_ids = ['region_%04d' % i for i in range(len(co_text_all_org))]
|
||||
return ordered, region_ids
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
def return_list_of_contours_with_desired_order(self, ls_cons, sorted_indexes):
|
||||
return list(np.array(ls_cons)[np.array(sorted_indexes)])
|
||||
|
||||
def return_it_in_two_groups(self, x_differential):
|
||||
split = [ind if x_differential[ind]!=x_differential[ind+1] else -1
|
||||
for ind in range(len(x_differential)-1)]
|
||||
split_masked = list( np.array(split[:])[np.array(split[:])!=-1] )
|
||||
if 0 not in split_masked:
|
||||
split_masked.insert(0, -1)
|
||||
split_masked.append(len(x_differential)-1)
|
||||
|
||||
split_masked = np.array(split_masked) +1
|
||||
|
||||
sums = [np.sum(x_differential[split_masked[ind]:split_masked[ind+1]])
|
||||
for ind in range(len(split_masked)-1)]
|
||||
|
||||
indexes_to_bec_changed = [ind if (np.abs(sums[ind-1]) > np.abs(sums[ind]) and
|
||||
np.abs(sums[ind+1]) > np.abs(sums[ind])) else -1
|
||||
for ind in range(1,len(sums)-1)]
|
||||
indexes_to_bec_changed_filtered = np.array(indexes_to_bec_changed)[np.array(indexes_to_bec_changed)!=-1]
|
||||
|
||||
x_differential_new = np.copy(x_differential)
|
||||
for i in indexes_to_bec_changed_filtered:
|
||||
i_slice = slice(split_masked[i], split_masked[i+1])
|
||||
x_differential_new[i_slice] = -1 * np.array(x_differential)[i_slice]
|
||||
|
||||
return x_differential_new
|
||||
|
||||
def filter_contours_inside_a_bigger_one(self, contours, contours_d_ordered, image,
|
||||
marginal_cnts=None, type_contour="textregion"):
|
||||
if type_contour == "textregion":
|
||||
|
|
|
|||
|
|
@ -10,14 +10,14 @@ Image enhancer. The output can be written as same scale of input or in new predi
|
|||
import logging
|
||||
import os
|
||||
import time
|
||||
from typing import Dict, Optional
|
||||
from typing import Optional
|
||||
from pathlib import Path
|
||||
import gc
|
||||
|
||||
import cv2
|
||||
from keras.models import Model
|
||||
import numpy as np
|
||||
import tensorflow as tf
|
||||
import tensorflow as tf # type: ignore
|
||||
from skimage.morphology import skeletonize
|
||||
|
||||
from .model_zoo import EynollahModelZoo
|
||||
|
|
@ -27,7 +27,6 @@ from .utils import (
|
|||
is_image_filename,
|
||||
crop_image_inside_box
|
||||
)
|
||||
from .patch_encoder import PatchEncoder, Patches
|
||||
|
||||
DPI_THRESHOLD = 298
|
||||
KERNEL = np.ones((5, 5), np.uint8)
|
||||
|
|
@ -91,9 +90,6 @@ class Enhancer:
|
|||
key += '_uint8'
|
||||
return self._imgs[key].copy()
|
||||
|
||||
def isNaN(self, num):
|
||||
return num != num
|
||||
|
||||
def predict_enhancement(self, img):
|
||||
self.logger.debug("enter predict_enhancement")
|
||||
|
||||
|
|
|
|||
|
|
@ -5,8 +5,6 @@ import numpy as np
|
|||
import cv2
|
||||
from scipy.signal import find_peaks
|
||||
from scipy.ndimage import gaussian_filter1d
|
||||
from multiprocessing import Process, Queue, cpu_count
|
||||
from multiprocessing import Pool
|
||||
from .rotate import rotate_image
|
||||
from .resize import resize_image
|
||||
from .contour import (
|
||||
|
|
@ -20,9 +18,7 @@ from .contour import (
|
|||
from .shm import share_ndarray, wrap_ndarray_shared
|
||||
from . import (
|
||||
find_num_col_deskew,
|
||||
crop_image_inside_box,
|
||||
box2rect,
|
||||
box2slice,
|
||||
)
|
||||
|
||||
def dedup_separate_lines(img_patch, contour_text_interest, thetha, axis):
|
||||
|
|
@ -1590,65 +1586,6 @@ def get_smallest_skew(img, sigma_des, angles, logger=None, plotter=None, map=map
|
|||
var = 0
|
||||
return angle, var
|
||||
|
||||
@wrap_ndarray_shared(kw='textline_mask_tot_ea')
|
||||
def do_work_of_slopes_new(
|
||||
box_text, contour, contour_par,
|
||||
textline_mask_tot_ea=None, slope_deskew=0.0,
|
||||
logger=None, MAX_SLOPE=999, KERNEL=None, plotter=None
|
||||
):
|
||||
if KERNEL is None:
|
||||
KERNEL = np.ones((5, 5), np.uint8)
|
||||
if logger is None:
|
||||
logger = getLogger(__package__)
|
||||
logger.debug('enter do_work_of_slopes_new')
|
||||
|
||||
x, y, w, h = box_text
|
||||
crop_coor = box2rect(box_text)
|
||||
mask_textline = np.zeros(textline_mask_tot_ea.shape)
|
||||
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 = all_text_region_raw[y: y + h, x: x + w].astype(np.uint8)
|
||||
img_int_p = all_text_region_raw[:,:]
|
||||
img_int_p = cv2.erode(img_int_p, KERNEL, iterations=2)
|
||||
|
||||
if not np.prod(img_int_p.shape) or img_int_p.shape[0] /img_int_p.shape[1] < 0.1:
|
||||
slope = 0
|
||||
slope_for_all = slope_deskew
|
||||
all_text_region_raw = textline_mask_tot_ea[y: y + h, x: x + w]
|
||||
cnt_clean_rot = textline_contours_postprocessing(all_text_region_raw, slope_for_all, contour_par, box_text, 0)
|
||||
else:
|
||||
try:
|
||||
textline_con, hierarchy = return_contours_of_image(img_int_p)
|
||||
textline_con_fil = filter_contours_area_of_image(img_int_p, textline_con,
|
||||
hierarchy,
|
||||
max_area=1, min_area=0.00008)
|
||||
y_diff_mean = find_contours_mean_y_diff(textline_con_fil) if len(textline_con_fil) > 1 else np.NaN
|
||||
if np.isnan(y_diff_mean):
|
||||
slope_for_all = MAX_SLOPE
|
||||
else:
|
||||
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, logger=logger, plotter=plotter)
|
||||
if abs(slope_for_all) <= 0.5:
|
||||
slope_for_all = slope_deskew
|
||||
except:
|
||||
logger.exception("cannot determine angle of contours")
|
||||
slope_for_all = MAX_SLOPE
|
||||
|
||||
if slope_for_all == MAX_SLOPE:
|
||||
slope_for_all = slope_deskew
|
||||
slope = slope_for_all
|
||||
mask_only_con_region = np.zeros(textline_mask_tot_ea.shape)
|
||||
mask_only_con_region = cv2.fillPoly(mask_only_con_region, pts=[contour_par], color=(1, 1, 1))
|
||||
|
||||
all_text_region_raw = textline_mask_tot_ea[y: y + h, x: x + w].copy()
|
||||
mask_only_con_region = mask_only_con_region[y: y + h, x: x + w]
|
||||
|
||||
all_text_region_raw[mask_only_con_region == 0] = 0
|
||||
cnt_clean_rot = textline_contours_postprocessing(all_text_region_raw, slope_for_all, contour_par, box_text)
|
||||
|
||||
return cnt_clean_rot, crop_coor, slope
|
||||
|
||||
@wrap_ndarray_shared(kw='textline_mask_tot_ea')
|
||||
@wrap_ndarray_shared(kw='mask_texts_only')
|
||||
def do_work_of_slopes_new_curved(
|
||||
|
|
|
|||
|
|
@ -4,7 +4,6 @@ from pathlib import Path
|
|||
import os.path
|
||||
from typing import Optional
|
||||
import logging
|
||||
import xml.etree.ElementTree as ET
|
||||
from .utils.xml import create_page_xml, xml_reading_order
|
||||
from .utils.counter import EynollahIdCounter
|
||||
|
||||
|
|
@ -19,7 +18,6 @@ from ocrd_models.ocrd_page import (
|
|||
SeparatorRegionType,
|
||||
to_xml
|
||||
)
|
||||
import numpy as np
|
||||
|
||||
class EynollahXmlWriter:
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue