qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-06-08 19:59:56 +02:00
Code Issues Projects Releases Wiki Activity

table detection completed, enhanced images can be now written to output

Browse source
This commit is contained in:
vahid 2021-07-09 10:23:45 -04:00
parent a5c940705a
commit c67e155431
4 changed files with 55 additions and 31 deletions
Download patch file Download diff file Expand all files Collapse all files

8
qurator/eynollah/cli.py
View file

@ -124,11 +124,11 @@ def main(
if log_level:
setOverrideLogLevel(log_level)
initLogging()
if not enable_plotting and (save_layout or save_deskewed or save_all or save_images):
print("Error: You used one of -sl, -sd, -sa or -si but did not enable plotting with -ep")
if not enable_plotting and (save_layout or save_deskewed or save_all or save_images or allow_enhancement):
print("Error: You used one of -sl, -sd, -sa or -si or -ae but did not enable plotting with -ep")
sys.exit(1)
elif enable_plotting and not (save_layout or save_deskewed or save_all or save_images):
print("Error: You used -ep to enable plotting but set none of -sl, -sd, -sa or -si")
elif enable_plotting and not (save_layout or save_deskewed or save_all or save_images or allow_enhancement):
print("Error: You used -ep to enable plotting but set none of -sl, -sd, -sa or -si or -ae")
sys.exit(1)
eynollah = Eynollah(
image_filename=image,

66
qurator/eynollah/eynollah.py
View file

@ -28,6 +28,7 @@ tf.get_logger().setLevel("ERROR")
warnings.filterwarnings("ignore")
from scipy.signal import find_peaks
import matplotlib.pyplot as plt
from scipy.ndimage import gaussian_filter1d
from .utils.contour import (
filter_contours_area_of_image,
@ -119,6 +120,7 @@ class Eynollah:
self.allow_scaling = allow_scaling
self.headers_off = headers_off
self.plotter = None if not enable_plotting else EynollahPlotter(
dir_out=self.dir_out,
dir_of_all=dir_of_all,
dir_of_deskewed=dir_of_deskewed,
dir_of_cropped_images=dir_of_cropped_images,
@ -1636,7 +1638,7 @@ class Eynollah:
x, y, w, h = cv2.boundingRect(contours[i])
iou = cnt_size[i] /float(w*h) *100
if iou<60:
if iou<80:
layout_contour = np.zeros((layout_org.shape[0], layout_org.shape[1]))
layout_contour= cv2.fillPoly(layout_contour,pts=[contours[i]] ,color=(1,1,1))
@ -1670,8 +1672,9 @@ class Eynollah:
only_recent_contour_image= cv2.fillPoly(only_recent_contour_image,pts=[contours_sep[ji]] ,color=(1,1,1))
table_pixels_masked_from_early_pre = only_recent_contour_image[:,:]*table_prediction_early[:,:]
iou_in = table_pixels_masked_from_early_pre.sum() /float(only_recent_contour_image.sum()) *100
#print(iou_in,'iou_in_in1')
if iou_in>20:
if iou_in>30:
layout_org= cv2.fillPoly(layout_org,pts=[contours_sep[ji]] ,color=(pixel_tabel,pixel_tabel,pixel_tabel))
else:
pass
@ -1687,8 +1690,8 @@ class Eynollah:
table_pixels_masked_from_early_pre = only_recent_contour_image[:,:]*table_prediction_early[:,:]
iou_in = table_pixels_masked_from_early_pre.sum() /float(only_recent_contour_image.sum()) *100
if iou_in>20:
#print(iou_in,'iou_in')
if iou_in>30:
layout_org= cv2.fillPoly(layout_org,pts=[contours[i]] ,color=(pixel_tabel,pixel_tabel,pixel_tabel))
else:
pass
@ -1719,6 +1722,13 @@ class Eynollah:
def add_tables_heuristic_to_layout(self, image_regions_eraly_p,boxes, slope_mean_hor, spliter_y,peaks_neg_tot, image_revised, num_col_classifier, min_area, pixel_line):
pixel_table =10
image_revised_1 = self.delete_separator_around(spliter_y, peaks_neg_tot, image_revised, pixel_line, pixel_table)
try:
image_revised_1[:,:30][image_revised_1[:,:30]==pixel_line] = 0
image_revised_1[:,image_revised_1.shape[1]-30:][image_revised_1[:,image_revised_1.shape[1]-30:]==pixel_line] = 0
except:
pass
img_comm_e = np.zeros(image_revised_1.shape)
img_comm = np.repeat(img_comm_e[:, :, np.newaxis], 3, axis=2)
@ -1840,6 +1850,12 @@ class Eynollah:
if num_col_classifier < 4 and num_col_classifier > 2:
prediction_table = self.do_prediction(patches, img, model_region)
pre_updown = self.do_prediction(patches, cv2.flip(img[:,:,:], -1), model_region)
pre_updown = cv2.flip(pre_updown, -1)
prediction_table[:,:,0][pre_updown[:,:,0]==1]=1
prediction_table = prediction_table.astype(np.int16)
elif num_col_classifier ==2:
height_ext = 0#int( img.shape[0]/4. )
h_start = int(height_ext/2.)
@ -1853,8 +1869,14 @@ class Eynollah:
img_new[h_start:h_start+img.shape[0] ,w_start: w_start+img.shape[1], : ] =img[:,:,:]
prediction_ext = self.do_prediction(patches, img_new, model_region)
prediction_table = prediction_ext[h_start:h_start+img.shape[0] ,w_start: w_start+img.shape[1], : ]
pre_updown = self.do_prediction(patches, cv2.flip(img_new[:,:,:], -1), model_region)
pre_updown = cv2.flip(pre_updown, -1)
prediction_table = prediction_ext[h_start:h_start+img.shape[0] ,w_start: w_start+img.shape[1], : ]
prediction_table_updown = pre_updown[h_start:h_start+img.shape[0] ,w_start: w_start+img.shape[1], : ]
prediction_table[:,:,0][prediction_table_updown[:,:,0]==1]=1
prediction_table = prediction_table.astype(np.int16)
elif num_col_classifier ==1:
@ -1870,26 +1892,16 @@ class Eynollah:
img_new[h_start:h_start+img.shape[0] ,w_start: w_start+img.shape[1], : ] =img[:,:,:]
prediction_ext = self.do_prediction(patches, img_new, model_region)
pre_updown = self.do_prediction(patches, cv2.flip(img_new[:,:,:], -1), model_region)
pre_updown = cv2.flip(pre_updown, -1)
prediction_table = prediction_ext[h_start:h_start+img.shape[0] ,w_start: w_start+img.shape[1], : ]
prediction_table_updown = pre_updown[h_start:h_start+img.shape[0] ,w_start: w_start+img.shape[1], : ]
prediction_table[:,:,0][prediction_table_updown[:,:,0]==1]=1
prediction_table = prediction_table.astype(np.int16)
elif num_col_classifier ==60:
prediction_table = np.zeros(img.shape)
img_w_half = int(img.shape[1]/2.)
img_h_half = int(img.shape[0]/2.)
pre1 = self.do_prediction(patches, img[0:img_h_half,0:img_w_half,:], model_region)
pre2 = self.do_prediction(patches, img[0:img_h_half,img_w_half:,:], model_region)
pre3 = self.do_prediction(patches, img[img_h_half:,0:img_w_half,:], model_region)
pre4 = self.do_prediction(patches, img[img_h_half:,img_w_half:,:], model_region)
prediction_table[0:img_h_half,0:img_w_half,:] = pre1[:,:,:]
prediction_table[0:img_h_half,img_w_half:,:] = pre2[:,:,:]
prediction_table[img_h_half:,0:img_w_half,:] = pre3[:,:,:]
prediction_table[img_h_half:,img_w_half:,:] = pre4[:,:,:]
prediction_table = prediction_table.astype(np.int16)
else:
prediction_table = np.zeros(img.shape)
img_w_half = int(img.shape[1]/2.)
@ -1899,14 +1911,20 @@ class Eynollah:
pre_full = self.do_prediction(patches, img[:,:,:], model_region)
pre_updown = self.do_prediction(patches, cv2.flip(img[:,:,:], -1), model_region)
pre_updown = cv2.flip(pre_updown, -1)
prediction_table_full_erode = cv2.erode(pre_full[:,:,0], KERNEL, iterations=4)
prediction_table_full_erode = cv2.dilate(prediction_table_full_erode, KERNEL, iterations=4)
prediction_table_full_updown_erode = cv2.erode(pre_updown[:,:,0], KERNEL, iterations=4)
prediction_table_full_updown_erode = cv2.dilate(prediction_table_full_updown_erode, KERNEL, iterations=4)
prediction_table[:,0:img_w_half,:] = pre1[:,:,:]
prediction_table[:,img_w_half:,:] = pre2[:,:,:]
prediction_table[:,:,0][prediction_table_full_erode[:,:]==1]=1
prediction_table[:,:,0][prediction_table_full_updown_erode[:,:]==1]=1
prediction_table = prediction_table.astype(np.int16)
#prediction_table_erode = cv2.erode(prediction_table[:,:,0], self.kernel, iterations=6)
@ -1977,6 +1995,8 @@ class Eynollah:
if self.allow_enhancement:
img_res = img_res.astype(np.uint8)
self.get_image_and_scales(img_org, img_res, scale)
if self.plotter:
self.plotter.save_enhanced_image(img_res)
else:
self.get_image_and_scales_after_enhancing(img_org, img_res)
else:
@ -2100,6 +2120,7 @@ class Eynollah:
if self.tables:
if np.abs(slope_deskew) < SLOPE_THRESHOLD:
img_revised_tab = np.copy(img_revised_tab2[:,:,0])
img_revised_tab[:,:][(text_regions_p[:,:] == 1) & (img_revised_tab[:,:] != 10)] = 1
else:
img_revised_tab = np.copy(text_regions_p[:,:])
img_revised_tab[:,:][img_revised_tab[:,:] == 10] = 0
@ -2310,7 +2331,6 @@ class Eynollah:
textline_mask_tot, text_regions_p, image_page_rotated = self.run_marginals(image_page, textline_mask_tot_ea, mask_images, mask_lines, num_col_classifier, slope_deskew, text_regions_p_1, table_prediction)
self.logger.info("detection of marginals took %ss", str(time.time() - t1))
t1 = time.time()
if not self.full_layout:
polygons_of_images, img_revised_tab, text_regions_p_1_n, textline_mask_tot_d, regions_without_separators_d, boxes, boxes_d, polygons_of_marginals, contours_tables = self.run_boxes_no_full_layout(image_page, textline_mask_tot, text_regions_p, slope_deskew, num_col_classifier, table_prediction, erosion_hurts)

4
qurator/eynollah/plot.py
View file

@ -17,6 +17,7 @@ class EynollahPlotter():
def __init__(
self,
*,
dir_out,
dir_of_all,
dir_of_deskewed,
dir_of_layout,
@ -26,6 +27,7 @@ class EynollahPlotter():
scale_x=1,
scale_y=1,
):
self.dir_out = dir_out
self.dir_of_all = dir_of_all
self.dir_of_layout = dir_of_layout
self.dir_of_cropped_images = dir_of_cropped_images
@ -125,6 +127,8 @@ class EynollahPlotter():
def save_page_image(self, image_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)
def save_enhanced_image(self, img_res):
cv2.imwrite(os.path.join(self.dir_out, self.image_filename_stem + "_enhanced.png"), img_res)
def save_plot_of_textline_density(self, img_patch_org):
if self.dir_of_all is not None:

4
qurator/eynollah/writer.py
View file

@ -194,9 +194,9 @@ class EynollahXmlWriter():
page.add_TableRegion(tab_region)
points_co = ''
for lmm in range(len(found_polygons_tables[mm])):
points_co += str(int((found_polygons_tables[mm][lmm,0,0] ) / self.scale_x))
points_co += str(int((found_polygons_tables[mm][lmm,0,0] + page_coord[2]) / self.scale_x))
points_co += ','
points_co += str(int((found_polygons_tables[mm][lmm,0,1] ) / self.scale_y))
points_co += str(int((found_polygons_tables[mm][lmm,0,1] + page_coord[0]) / self.scale_y))
points_co += ' '
tab_region.get_Coords().set_points(points_co[:-1])