mirror of
https://github.com/qurator-spk/eynollah.git
synced 2025-10-07 06:59:58 +02:00
dilate_textregions_contours: simplify (via shapely's Polygon.buffer()), ensure validity
This commit is contained in:
Robert Sachunsky
parent
a2359ea4c4
commit
09ece86f0d
2 changed files with 36 additions and 206 deletions
|
|
@ -27,6 +27,7 @@ from loky import ProcessPoolExecutor
|
||||||
import xml.etree.ElementTree as ET
|
import xml.etree.ElementTree as ET
|
||||||
import cv2
|
import cv2
|
||||||
import numpy as np
|
import numpy as np
|
||||||
|
from shapely.geometry import Polygon
|
||||||
from scipy.signal import find_peaks
|
from scipy.signal import find_peaks
|
||||||
from scipy.ndimage import gaussian_filter1d
|
from scipy.ndimage import gaussian_filter1d
|
||||||
from numba import cuda
|
from numba import cuda
|
||||||
|
|
@ -68,6 +69,7 @@ from .utils.contour import (
|
||||||
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,
|
||||||
get_textregion_contours_in_org_image_light,
|
get_textregion_contours_in_org_image_light,
|
||||||
|
make_valid,
|
||||||
return_contours_of_image,
|
return_contours_of_image,
|
||||||
return_contours_of_interested_region,
|
return_contours_of_interested_region,
|
||||||
return_contours_of_interested_region_by_min_size,
|
return_contours_of_interested_region_by_min_size,
|
||||||
|
|
@ -3670,211 +3672,15 @@ class Eynollah:
|
||||||
return x_differential_new
|
return x_differential_new
|
||||||
|
|
||||||
def dilate_textregions_contours_textline_version(self, all_found_textline_polygons):
|
def dilate_textregions_contours_textline_version(self, all_found_textline_polygons):
|
||||||
#print(all_found_textline_polygons)
|
return [[np.array(make_valid(Polygon(poly[:, 0]).buffer(5)).exterior.coords,
|
||||||
for j in range(len(all_found_textline_polygons)):
|
dtype=int)[:, np.newaxis]
|
||||||
for ij in range(len(all_found_textline_polygons[j])):
|
for poly in region]
|
||||||
con_ind = all_found_textline_polygons[j][ij]
|
for region in all_found_textline_polygons]
|
||||||
area = cv2.contourArea(con_ind)
|
|
||||||
con_ind = con_ind.astype(float)
|
|
||||||
|
|
||||||
x_differential = np.diff( con_ind[:,0,0])
|
|
||||||
y_differential = np.diff( con_ind[:,0,1])
|
|
||||||
|
|
||||||
x_differential = gaussian_filter1d(x_differential, 0.1)
|
|
||||||
y_differential = gaussian_filter1d(y_differential, 0.1)
|
|
||||||
|
|
||||||
x_min = float(np.min( con_ind[:,0,0] ))
|
|
||||||
y_min = float(np.min( con_ind[:,0,1] ))
|
|
||||||
|
|
||||||
x_max = float(np.max( con_ind[:,0,0] ))
|
|
||||||
y_max = float(np.max( con_ind[:,0,1] ))
|
|
||||||
|
|
||||||
x_differential_mask_nonzeros = [ ind/abs(ind) if ind!=0 else ind for ind in x_differential]
|
|
||||||
y_differential_mask_nonzeros = [ ind/abs(ind) if ind!=0 else ind for ind in y_differential]
|
|
||||||
|
|
||||||
abs_diff=abs(abs(x_differential)- abs(y_differential) )
|
|
||||||
|
|
||||||
inc_x = np.zeros(len(x_differential)+1)
|
|
||||||
inc_y = np.zeros(len(x_differential)+1)
|
|
||||||
|
|
||||||
if (y_max-y_min) <= (x_max-x_min):
|
|
||||||
dilation_m1 = round(area / (x_max-x_min) * 0.12)
|
|
||||||
else:
|
|
||||||
dilation_m1 = round(area / (y_max-y_min) * 0.12)
|
|
||||||
|
|
||||||
if dilation_m1>8:
|
|
||||||
dilation_m1 = 8
|
|
||||||
if dilation_m1<6:
|
|
||||||
dilation_m1 = 6
|
|
||||||
#print(dilation_m1, 'dilation_m1')
|
|
||||||
dilation_m1 = 6
|
|
||||||
dilation_m2 = int(dilation_m1/2.) +1
|
|
||||||
|
|
||||||
for i in range(len(x_differential)):
|
|
||||||
if abs_diff[i]==0:
|
|
||||||
inc_x[i+1] = dilation_m2*(-1*y_differential_mask_nonzeros[i])
|
|
||||||
inc_y[i+1] = dilation_m2*(x_differential_mask_nonzeros[i])
|
|
||||||
elif abs_diff[i]!=0 and x_differential_mask_nonzeros[i]==0 and y_differential_mask_nonzeros[i]!=0:
|
|
||||||
inc_x[i+1]= dilation_m1*(-1*y_differential_mask_nonzeros[i])
|
|
||||||
elif abs_diff[i]!=0 and x_differential_mask_nonzeros[i]!=0 and y_differential_mask_nonzeros[i]==0:
|
|
||||||
inc_y[i+1] = dilation_m1*(x_differential_mask_nonzeros[i])
|
|
||||||
|
|
||||||
elif abs_diff[i]!=0 and abs_diff[i]>=3:
|
|
||||||
if abs(x_differential[i])>abs(y_differential[i]):
|
|
||||||
inc_y[i+1] = dilation_m1*(x_differential_mask_nonzeros[i])
|
|
||||||
else:
|
|
||||||
inc_x[i+1]= dilation_m1*(-1*y_differential_mask_nonzeros[i])
|
|
||||||
else:
|
|
||||||
inc_x[i+1] = dilation_m2*(-1*y_differential_mask_nonzeros[i])
|
|
||||||
inc_y[i+1] = dilation_m2*(x_differential_mask_nonzeros[i])
|
|
||||||
|
|
||||||
inc_x[0] = inc_x[-1]
|
|
||||||
inc_y[0] = inc_y[-1]
|
|
||||||
|
|
||||||
con_scaled = con_ind*1
|
|
||||||
|
|
||||||
con_scaled[:,0, 0] = con_ind[:,0,0] + np.array(inc_x)[:]
|
|
||||||
con_scaled[:,0, 1] = con_ind[:,0,1] + np.array(inc_y)[:]
|
|
||||||
|
|
||||||
con_scaled[:,0, 1][con_scaled[:,0, 1]<0] = 0
|
|
||||||
con_scaled[:,0, 0][con_scaled[:,0, 0]<0] = 0
|
|
||||||
|
|
||||||
area_scaled = cv2.contourArea(con_scaled.astype(np.int32))
|
|
||||||
|
|
||||||
con_ind = con_ind.astype(np.int32)
|
|
||||||
|
|
||||||
results = [cv2.pointPolygonTest(con_ind, (con_scaled[ind,0, 0], con_scaled[ind,0, 1]), False)
|
|
||||||
for ind in range(len(con_scaled[:,0, 1])) ]
|
|
||||||
results = np.array(results)
|
|
||||||
#print(results,'results')
|
|
||||||
results[results==0] = 1
|
|
||||||
|
|
||||||
diff_result = np.diff(results)
|
|
||||||
|
|
||||||
indices_2 = [ind for ind in range(len(diff_result)) if diff_result[ind]==2]
|
|
||||||
indices_m2 = [ind for ind in range(len(diff_result)) if diff_result[ind]==-2]
|
|
||||||
|
|
||||||
if results[0]==1:
|
|
||||||
con_scaled[:indices_m2[0]+1,0, 1] = con_ind[:indices_m2[0]+1,0,1]
|
|
||||||
con_scaled[:indices_m2[0]+1,0, 0] = con_ind[:indices_m2[0]+1,0,0]
|
|
||||||
#indices_2 = indices_2[1:]
|
|
||||||
indices_m2 = indices_m2[1:]
|
|
||||||
|
|
||||||
if len(indices_2)>len(indices_m2):
|
|
||||||
con_scaled[indices_2[-1]+1:,0, 1] = con_ind[indices_2[-1]+1:,0,1]
|
|
||||||
con_scaled[indices_2[-1]+1:,0, 0] = con_ind[indices_2[-1]+1:,0,0]
|
|
||||||
indices_2 = indices_2[:-1]
|
|
||||||
|
|
||||||
for ii in range(len(indices_2)):
|
|
||||||
con_scaled[indices_2[ii]+1:indices_m2[ii]+1,0, 1] = con_scaled[indices_2[ii],0, 1]
|
|
||||||
con_scaled[indices_2[ii]+1:indices_m2[ii]+1,0, 0] = con_scaled[indices_2[ii],0, 0]
|
|
||||||
|
|
||||||
all_found_textline_polygons[j][ij][:,0,1] = con_scaled[:,0, 1]
|
|
||||||
all_found_textline_polygons[j][ij][:,0,0] = con_scaled[:,0, 0]
|
|
||||||
return all_found_textline_polygons
|
|
||||||
|
|
||||||
def dilate_textregions_contours(self, all_found_textline_polygons):
|
def dilate_textregions_contours(self, all_found_textline_polygons):
|
||||||
#print(all_found_textline_polygons)
|
return [np.array(make_valid(Polygon(poly[:, 0])).buffer(5).exterior.coords,
|
||||||
for j in range(len(all_found_textline_polygons)):
|
dtype=int)[:, np.newaxis]
|
||||||
con_ind = all_found_textline_polygons[j]
|
for poly in all_found_textline_polygons]
|
||||||
#print(len(con_ind[:,0,0]),'con_ind[:,0,0]')
|
|
||||||
area = cv2.contourArea(con_ind)
|
|
||||||
con_ind = con_ind.astype(float)
|
|
||||||
|
|
||||||
x_differential = np.diff( con_ind[:,0,0])
|
|
||||||
y_differential = np.diff( con_ind[:,0,1])
|
|
||||||
|
|
||||||
x_differential = gaussian_filter1d(x_differential, 0.1)
|
|
||||||
y_differential = gaussian_filter1d(y_differential, 0.1)
|
|
||||||
|
|
||||||
x_min = float(np.min( con_ind[:,0,0] ))
|
|
||||||
y_min = float(np.min( con_ind[:,0,1] ))
|
|
||||||
|
|
||||||
x_max = float(np.max( con_ind[:,0,0] ))
|
|
||||||
y_max = float(np.max( con_ind[:,0,1] ))
|
|
||||||
|
|
||||||
x_differential_mask_nonzeros = [ ind/abs(ind) if ind!=0 else ind for ind in x_differential]
|
|
||||||
y_differential_mask_nonzeros = [ ind/abs(ind) if ind!=0 else ind for ind in y_differential]
|
|
||||||
|
|
||||||
abs_diff=abs(abs(x_differential)- abs(y_differential) )
|
|
||||||
|
|
||||||
inc_x = np.zeros(len(x_differential)+1)
|
|
||||||
inc_y = np.zeros(len(x_differential)+1)
|
|
||||||
|
|
||||||
if (y_max-y_min) <= (x_max-x_min):
|
|
||||||
dilation_m1 = round(area / (x_max-x_min) * 0.12)
|
|
||||||
else:
|
|
||||||
dilation_m1 = round(area / (y_max-y_min) * 0.12)
|
|
||||||
|
|
||||||
if dilation_m1>8:
|
|
||||||
dilation_m1 = 8
|
|
||||||
if dilation_m1<6:
|
|
||||||
dilation_m1 = 6
|
|
||||||
#print(dilation_m1, 'dilation_m1')
|
|
||||||
dilation_m1 = 6
|
|
||||||
dilation_m2 = int(dilation_m1/2.) +1
|
|
||||||
|
|
||||||
for i in range(len(x_differential)):
|
|
||||||
if abs_diff[i]==0:
|
|
||||||
inc_x[i+1] = dilation_m2*(-1*y_differential_mask_nonzeros[i])
|
|
||||||
inc_y[i+1] = dilation_m2*(x_differential_mask_nonzeros[i])
|
|
||||||
elif abs_diff[i]!=0 and x_differential_mask_nonzeros[i]==0 and y_differential_mask_nonzeros[i]!=0:
|
|
||||||
inc_x[i+1]= dilation_m1*(-1*y_differential_mask_nonzeros[i])
|
|
||||||
elif abs_diff[i]!=0 and x_differential_mask_nonzeros[i]!=0 and y_differential_mask_nonzeros[i]==0:
|
|
||||||
inc_y[i+1] = dilation_m1*(x_differential_mask_nonzeros[i])
|
|
||||||
|
|
||||||
elif abs_diff[i]!=0 and abs_diff[i]>=3:
|
|
||||||
if abs(x_differential[i])>abs(y_differential[i]):
|
|
||||||
inc_y[i+1] = dilation_m1*(x_differential_mask_nonzeros[i])
|
|
||||||
else:
|
|
||||||
inc_x[i+1]= dilation_m1*(-1*y_differential_mask_nonzeros[i])
|
|
||||||
else:
|
|
||||||
inc_x[i+1] = dilation_m2*(-1*y_differential_mask_nonzeros[i])
|
|
||||||
inc_y[i+1] = dilation_m2*(x_differential_mask_nonzeros[i])
|
|
||||||
|
|
||||||
inc_x[0] = inc_x[-1]
|
|
||||||
inc_y[0] = inc_y[-1]
|
|
||||||
|
|
||||||
con_scaled = con_ind*1
|
|
||||||
|
|
||||||
con_scaled[:,0, 0] = con_ind[:,0,0] + np.array(inc_x)[:]
|
|
||||||
con_scaled[:,0, 1] = con_ind[:,0,1] + np.array(inc_y)[:]
|
|
||||||
|
|
||||||
con_scaled[:,0, 1][con_scaled[:,0, 1]<0] = 0
|
|
||||||
con_scaled[:,0, 0][con_scaled[:,0, 0]<0] = 0
|
|
||||||
|
|
||||||
area_scaled = cv2.contourArea(con_scaled.astype(np.int32))
|
|
||||||
|
|
||||||
con_ind = con_ind.astype(np.int32)
|
|
||||||
|
|
||||||
results = [cv2.pointPolygonTest(con_ind, (con_scaled[ind,0, 0], con_scaled[ind,0, 1]), False)
|
|
||||||
for ind in range(len(con_scaled[:,0, 1])) ]
|
|
||||||
results = np.array(results)
|
|
||||||
#print(results,'results')
|
|
||||||
results[results==0] = 1
|
|
||||||
|
|
||||||
diff_result = np.diff(results)
|
|
||||||
indices_2 = [ind for ind in range(len(diff_result)) if diff_result[ind]==2]
|
|
||||||
indices_m2 = [ind for ind in range(len(diff_result)) if diff_result[ind]==-2]
|
|
||||||
|
|
||||||
if results[0]==1:
|
|
||||||
con_scaled[:indices_m2[0]+1,0, 1] = con_ind[:indices_m2[0]+1,0,1]
|
|
||||||
con_scaled[:indices_m2[0]+1,0, 0] = con_ind[:indices_m2[0]+1,0,0]
|
|
||||||
#indices_2 = indices_2[1:]
|
|
||||||
indices_m2 = indices_m2[1:]
|
|
||||||
|
|
||||||
if len(indices_2)>len(indices_m2):
|
|
||||||
con_scaled[indices_2[-1]+1:,0, 1] = con_ind[indices_2[-1]+1:,0,1]
|
|
||||||
con_scaled[indices_2[-1]+1:,0, 0] = con_ind[indices_2[-1]+1:,0,0]
|
|
||||||
indices_2 = indices_2[:-1]
|
|
||||||
|
|
||||||
for ii in range(len(indices_2)):
|
|
||||||
con_scaled[indices_2[ii]+1:indices_m2[ii]+1,0, 1] = con_scaled[indices_2[ii],0, 1]
|
|
||||||
con_scaled[indices_2[ii]+1:indices_m2[ii]+1,0, 0] = con_scaled[indices_2[ii],0, 0]
|
|
||||||
|
|
||||||
all_found_textline_polygons[j][:,0,1] = con_scaled[:,0, 1]
|
|
||||||
all_found_textline_polygons[j][:,0,0] = con_scaled[:,0, 0]
|
|
||||||
return all_found_textline_polygons
|
|
||||||
|
|
||||||
def dilate_textline_contours(self, all_found_textline_polygons):
|
def dilate_textline_contours(self, all_found_textline_polygons):
|
||||||
for j in range(len(all_found_textline_polygons)):
|
for j in range(len(all_found_textline_polygons)):
|
||||||
|
|
|
||||||
|
|
@ -1,7 +1,7 @@
|
||||||
from functools import partial
|
from functools import partial
|
||||||
import cv2
|
import cv2
|
||||||
import numpy as np
|
import numpy as np
|
||||||
from shapely import geometry
|
from shapely.geometry import Polygon
|
||||||
|
|
||||||
from .rotate import rotate_image, rotation_image_new
|
from .rotate import rotate_image, rotation_image_new
|
||||||
|
|
||||||
|
|
@ -43,7 +43,7 @@ def filter_contours_area_of_image(image, contours, hierarchy, max_area, min_area
|
||||||
if len(c) < 3: # A polygon cannot have less than 3 points
|
if len(c) < 3: # A polygon cannot have less than 3 points
|
||||||
continue
|
continue
|
||||||
|
|
||||||
polygon = geometry.Polygon([point[0] for point in c])
|
polygon = Polygon([point[0] for point in c])
|
||||||
area = polygon.area
|
area = polygon.area
|
||||||
if (area >= min_area * np.prod(image.shape[:2]) and
|
if (area >= min_area * np.prod(image.shape[:2]) and
|
||||||
area <= max_area * np.prod(image.shape[:2]) and
|
area <= max_area * np.prod(image.shape[:2]) and
|
||||||
|
|
@ -58,7 +58,7 @@ def filter_contours_area_of_image_tables(image, contours, hierarchy, max_area, m
|
||||||
if len(c) < 3: # A polygon cannot have less than 3 points
|
if len(c) < 3: # A polygon cannot have less than 3 points
|
||||||
continue
|
continue
|
||||||
|
|
||||||
polygon = geometry.Polygon([point[0] for point in c])
|
polygon = Polygon([point[0] for point in c])
|
||||||
# area = cv2.contourArea(c)
|
# area = cv2.contourArea(c)
|
||||||
area = polygon.area
|
area = polygon.area
|
||||||
##print(np.prod(thresh.shape[:2]))
|
##print(np.prod(thresh.shape[:2]))
|
||||||
|
|
@ -332,3 +332,27 @@ def return_contours_of_interested_region_by_size(region_pre_p, pixel, min_area,
|
||||||
|
|
||||||
return img_ret[:, :, 0]
|
return img_ret[:, :, 0]
|
||||||
|
|
||||||
|
def make_valid(polygon: Polygon) -> Polygon:
|
||||||
|
"""Ensures shapely.geometry.Polygon object is valid by repeated rearrangement/simplification/enlargement."""
|
||||||
|
points = list(polygon.exterior.coords)
|
||||||
|
# try by re-arranging points
|
||||||
|
for split in range(1, len(points)):
|
||||||
|
if polygon.is_valid or polygon.simplify(polygon.area).is_valid:
|
||||||
|
break
|
||||||
|
# simplification may not be possible (at all) due to ordering
|
||||||
|
# in that case, try another starting point
|
||||||
|
polygon = Polygon(points[-split:]+points[:-split])
|
||||||
|
# try by simplification
|
||||||
|
for tolerance in range(int(polygon.area + 1.5)):
|
||||||
|
if polygon.is_valid:
|
||||||
|
break
|
||||||
|
# simplification may require a larger tolerance
|
||||||
|
polygon = polygon.simplify(tolerance + 1)
|
||||||
|
# try by enlarging
|
||||||
|
for tolerance in range(1, int(polygon.area + 2.5)):
|
||||||
|
if polygon.is_valid:
|
||||||
|
break
|
||||||
|
# enlargement may require a larger tolerance
|
||||||
|
polygon = polygon.buffer(tolerance)
|
||||||
|
assert polygon.is_valid, polygon.wkt
|
||||||
|
return polygon
|
||||||
|
|
|
||||||
Loading…
Add table
Add a link
Reference in a new issue