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

Merge branch 'main' into dockerfile

Browse Source
pull/137/head
kba 3 months ago
parent 478edc804a 4af0bc079c
commit 7eb1390583
6 changed files with 475 additions and 274 deletions
Show Stats Download Patch File Download Diff File

7
Makefile
Unescape Escape View File

@ -27,17 +27,14 @@ help:
models: models_eynollah
models_eynollah: models_eynollah.tar.gz
# tar xf models_eynollah_renamed.tar.gz --transform 's/models_eynollah_renamed/models_eynollah/'
# tar xf models_eynollah_renamed.tar.gz
# tar xf models_eynollah_renamed_savedmodel.tar.gz --transform 's/models_eynollah_renamed_savedmodel/models_eynollah/'
tar xf models_eynollah.tar.gz
models_eynollah.tar.gz:
# wget 'https://qurator-data.de/eynollah/2021-04-25/models_eynollah.tar.gz'
# wget 'https://qurator-data.de/eynollah/2022-04-05/models_eynollah_renamed.tar.gz'
# wget 'https://ocr-d.kba.cloud/2022-04-05.SavedModel.tar.gz'
# wget 'https://qurator-data.de/eynollah/2022-04-05/models_eynollah_renamed_savedmodel.tar.gz'
wget https://github.com/qurator-spk/eynollah/releases/download/v0.3.0/models_eynollah.tar.gz
# wget 'https://github.com/qurator-spk/eynollah/releases/download/v0.3.0/models_eynollah.tar.gz'
wget 'https://github.com/qurator-spk/eynollah/releases/download/v0.3.1/models_eynollah.tar.gz'
# Install with pip
install:

1
README.md
Unescape Escape View File

@ -71,6 +71,7 @@ The following options can be used to further configure the processing:
| `-cl` | apply contour detection for curved text lines instead of bounding boxes |
| `-ib` | apply binarization (the resulting image is saved to the output directory) |
| `-ep` | enable plotting (MUST always be used with `-sl`, `-sd`, `-sa`, `-si` or `-ae`) |
| `-eoi` | extract only images to output directory (other processing will not be done) |
| `-ho` | ignore headers for reading order dectection |
| `-si <directory>` | save image regions detected to this directory |
| `-sd <directory>` | save deskewed image to this directory |

11
src/eynollah/cli.py
Unescape Escape View File

@ -67,6 +67,12 @@ from eynollah.eynollah import Eynollah
is_flag=True,
help="If set, will plot intermediary files and images",
)
@click.option(
"--extract_only_images/--disable-extracting_only_images",
"-eoi/-noeoi",
is_flag=True,
help="If a directory is given, only images in documents will be cropped and saved there and the other processing will not be done",
)
@click.option(
"--allow-enhancement/--no-allow-enhancement",
"-ae/-noae",
@ -148,6 +154,7 @@ def main(
save_layout,
save_deskewed,
save_all,
extract_only_images,
save_page,
enable_plotting,
allow_enhancement,
@ -175,12 +182,16 @@ def main(
if textline_light and not light_version:
print('Error: You used -tll to enable light textline detection but -light is not enabled')
sys.exit(1)
if extract_only_images and (allow_enhancement or allow_scaling or light_version or curved_line or textline_light or full_layout or tables or right2left or headers_off) :
print('Error: You used -eoi which can not be enabled alongside light_version -light or allow_scaling -as or allow_enhancement -ae or curved_line -cl or textline_light -tll or full_layout -fl or tables -tab or right2left -r2l or headers_off -ho')
sys.exit(1)
eynollah = Eynollah(
image_filename=image,
dir_out=out,
dir_in=dir_in,
dir_models=model,
dir_of_cropped_images=save_images,
extract_only_images=extract_only_images,
dir_of_layout=save_layout,
dir_of_deskewed=save_deskewed,
dir_of_all=save_all,

200
src/eynollah/eynollah.py
Unescape Escape View File

@ -149,6 +149,7 @@ class Eynollah:
dir_out=None,
dir_in=None,
dir_of_cropped_images=None,
extract_only_images=False,
dir_of_layout=None,
dir_of_deskewed=None,
dir_of_all=None,
@ -196,6 +197,7 @@ class Eynollah:
self.allow_scaling = allow_scaling
self.headers_off = headers_off
self.light_version = light_version
self.extract_only_images = extract_only_images
self.ignore_page_extraction = ignore_page_extraction
self.pcgts = pcgts
if not dir_in:
@ -226,6 +228,7 @@ class Eynollah:
self.model_page_dir = dir_models + "/eynollah-page-extraction_20210425"
self.model_region_dir_p_ens = dir_models + "/eynollah-main-regions-ensembled_20210425"
self.model_region_dir_p_ens_light = dir_models + "/eynollah-main-regions_20220314"
self.model_region_dir_p_ens_light_only_images_extraction = dir_models + "/eynollah-main-regions_20231127_672_org_ens_11_13_16_17_18"
if self.textline_light:
self.model_textline_dir = dir_models + "/eynollah-textline_light_20210425"
else:
@ -250,7 +253,23 @@ class Eynollah:
self.ls_imgs = os.listdir(self.dir_in)
if dir_in and not light_version:
if dir_in and self.extract_only_images:
config = tf.compat.v1.ConfigProto()
config.gpu_options.allow_growth = True
session = tf.compat.v1.Session(config=config)
set_session(session)
self.model_page = self.our_load_model(self.model_page_dir)
self.model_classifier = self.our_load_model(self.model_dir_of_col_classifier)
self.model_bin = self.our_load_model(self.model_dir_of_binarization)
#self.model_textline = self.our_load_model(self.model_textline_dir)
self.model_region = self.our_load_model(self.model_region_dir_p_ens_light_only_images_extraction)
#self.model_region_fl_np = self.our_load_model(self.model_region_dir_fully_np)
#self.model_region_fl = self.our_load_model(self.model_region_dir_fully)
self.ls_imgs = os.listdir(self.dir_in)
if dir_in and not (light_version or self.extract_only_images):
config = tf.compat.v1.ConfigProto()
config.gpu_options.allow_growth = True
session = tf.compat.v1.Session(config=config)
@ -464,6 +483,27 @@ class Eynollah:
return img_new, num_column_is_classified
def calculate_width_height_by_columns_extract_only_images(self, img, num_col, width_early, label_p_pred):
self.logger.debug("enter calculate_width_height_by_columns")
if num_col == 1:
img_w_new = 700
elif num_col == 2:
img_w_new = 900
elif num_col == 3:
img_w_new = 1500
elif num_col == 4:
img_w_new = 1800
elif num_col == 5:
img_w_new = 2200
elif num_col == 6:
img_w_new = 2500
img_h_new = int(img.shape[0] / float(img.shape[1]) * img_w_new)
img_new = resize_image(img, img_h_new, img_w_new)
num_column_is_classified = True
return img_new, num_column_is_classified
def resize_image_with_column_classifier(self, is_image_enhanced, img_bin):
self.logger.debug("enter resize_image_with_column_classifier")
if self.input_binary:
@ -571,6 +611,7 @@ class Eynollah:
self.logger.info("Found %d columns (%s)", num_col, np.around(label_p_pred, decimals=5))
if not self.extract_only_images:
if dpi < DPI_THRESHOLD:
img_new, num_column_is_classified = self.calculate_width_height_by_columns(img, num_col, width_early, label_p_pred)
if light_version:
@ -582,6 +623,10 @@ class Eynollah:
num_column_is_classified = True
image_res = np.copy(img)
is_image_enhanced = False
else:
num_column_is_classified = True
image_res = np.copy(img)
is_image_enhanced = False
self.logger.debug("exit resize_and_enhance_image_with_column_classifier")
return is_image_enhanced, img, image_res, num_col, num_column_is_classified, img_bin
@ -868,7 +913,11 @@ class Eynollah:
seg_not_base = label_p_pred[0,:,:,4]
##seg2 = -label_p_pred[0,:,:,2]
if self.extract_only_images:
#seg_not_base[seg_not_base>0.3] =1
seg_not_base[seg_not_base>0.5] =1
seg_not_base[seg_not_base<1] =0
else:
seg_not_base[seg_not_base>0.03] =1
seg_not_base[seg_not_base<1] =0
@ -889,11 +938,8 @@ class Eynollah:
seg_line[seg_line>0.1] =1
seg_line[seg_line<1] =0
if not self.extract_only_images:
seg_background = label_p_pred[0,:,:,0]
##seg2 = -label_p_pred[0,:,:,2]
seg_background[seg_background>0.25] =1
seg_background[seg_background<1] =0
##seg = seg+seg2
@ -908,7 +954,8 @@ class Eynollah:
##plt.show()
#seg[seg==1]=0
#seg[seg_test==1]=1
seg[seg_not_base==1]=4
###seg[seg_not_base==1]=4
if not self.extract_only_images:
seg[seg_background==1]=0
seg[(seg_line==1) & (seg==0)]=3
seg_color = np.repeat(seg[:, :, np.newaxis], 3, axis=2)
@ -1574,6 +1621,124 @@ class Eynollah:
q.put(slopes_sub)
poly.put(poly_sub)
box_sub.put(boxes_sub_new)
def get_regions_light_v_extract_only_images(self,img,is_image_enhanced, num_col_classifier):
self.logger.debug("enter get_regions_extract_images_only")
erosion_hurts = False
img_org = np.copy(img)
img_height_h = img_org.shape[0]
img_width_h = img_org.shape[1]
if num_col_classifier == 1:
img_w_new = 700
elif num_col_classifier == 2:
img_w_new = 900
elif num_col_classifier == 3:
img_w_new = 1500
elif num_col_classifier == 4:
img_w_new = 1800
elif num_col_classifier == 5:
img_w_new = 2200
elif num_col_classifier == 6:
img_w_new = 2500
img_h_new = int(img.shape[0] / float(img.shape[1]) * img_w_new)
img_resized = resize_image(img,img_h_new, img_w_new )
if not self.dir_in:
model_region, session_region = self.start_new_session_and_model(self.model_region_dir_p_ens_light_only_images_extraction)
prediction_regions_org = self.do_prediction_new_concept(True, img_resized, model_region)
else:
prediction_regions_org = self.do_prediction_new_concept(True, img_resized, self.model_region)
#plt.imshow(prediction_regions_org[:,:,0])
#plt.show()
prediction_regions_org = resize_image(prediction_regions_org,img_height_h, img_width_h )
image_page, page_coord, cont_page = self.extract_page()
prediction_regions_org = prediction_regions_org[page_coord[0] : page_coord[1], page_coord[2] : page_coord[3]]
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_lines_xml, hir_lines_xml = return_contours_of_image(mask_lines_only)
polygons_lines_xml = textline_con_fil = filter_contours_area_of_image(mask_lines_only, polygons_lines_xml, hir_lines_xml, max_area=1, min_area=0.00001)
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))
text_regions_p_true[text_regions_p_true.shape[0]-15:text_regions_p_true.shape[0], :] = 0
text_regions_p_true[:, text_regions_p_true.shape[1]-15:text_regions_p_true.shape[1]] = 0
##polygons_of_images = return_contours_of_interested_region(text_regions_p_true, 2, 0.0001)
polygons_of_images = return_contours_of_interested_region(text_regions_p_true, 2, 0.001)
image_boundary_of_doc = np.zeros((text_regions_p_true.shape[0], text_regions_p_true.shape[1]))
###image_boundary_of_doc[:6, :] = 1
###image_boundary_of_doc[text_regions_p_true.shape[0]-6:text_regions_p_true.shape[0], :] = 1
###image_boundary_of_doc[:, :6] = 1
###image_boundary_of_doc[:, text_regions_p_true.shape[1]-6:text_regions_p_true.shape[1]] = 1
#plt.imshow(image_boundary_of_doc)
#plt.show()
polygons_of_images_fin = []
for ploy_img_ind in polygons_of_images:
"""
test_poly_image = np.zeros((text_regions_p_true.shape[0], text_regions_p_true.shape[1]))
test_poly_image = cv2.fillPoly(test_poly_image, pts = [ploy_img_ind], color=(1,1,1))
test_poly_image = test_poly_image[:,:] + image_boundary_of_doc[:,:]
test_poly_image_intersected_area = ( test_poly_image[:,:]==2 )*1
test_poly_image_intersected_area = test_poly_image_intersected_area.sum()
if test_poly_image_intersected_area==0:
##polygons_of_images_fin.append(ploy_img_ind)
x, y, w, h = cv2.boundingRect(ploy_img_ind)
box = [x, y, w, h]
_, page_coord_img = crop_image_inside_box(box, text_regions_p_true)
#cont_page.append(np.array([[page_coord[2], page_coord[0]], [page_coord[3], page_coord[0]], [page_coord[3], page_coord[1]], [page_coord[2], page_coord[1]]]))
polygons_of_images_fin.append(np.array([[page_coord_img[2], page_coord_img[0]], [page_coord_img[3], page_coord_img[0]], [page_coord_img[3], page_coord_img[1]], [page_coord_img[2], page_coord_img[1]]]) )
"""
x, y, w, h = cv2.boundingRect(ploy_img_ind)
if h < 150 or w < 150:
pass
else:
box = [x, y, w, h]
_, page_coord_img = crop_image_inside_box(box, text_regions_p_true)
#cont_page.append(np.array([[page_coord[2], page_coord[0]], [page_coord[3], page_coord[0]], [page_coord[3], page_coord[1]], [page_coord[2], page_coord[1]]]))
polygons_of_images_fin.append(np.array([[page_coord_img[2], page_coord_img[0]], [page_coord_img[3], page_coord_img[0]], [page_coord_img[3], page_coord_img[1]], [page_coord_img[2], page_coord_img[1]]]) )
return text_regions_p_true, erosion_hurts, polygons_lines_xml, polygons_of_images_fin, image_page, page_coord, cont_page
def get_regions_light_v(self,img,is_image_enhanced, num_col_classifier):
self.logger.debug("enter get_regions_light_v")
erosion_hurts = False
@ -2425,6 +2590,7 @@ class Eynollah:
prediction_table_erode = cv2.erode(prediction_table[:,:,0], KERNEL, iterations=20)
prediction_table_erode = cv2.dilate(prediction_table_erode, KERNEL, iterations=20)
return prediction_table_erode.astype(np.int16)
def run_graphics_and_columns_light(self, text_regions_p_1, textline_mask_tot_ea, num_col_classifier, num_column_is_classified, erosion_hurts):
img_g = self.imread(grayscale=True, uint8=True)
@ -2826,7 +2992,6 @@ class Eynollah:
"""
self.logger.debug("enter run")
t0_tot = time.time()
if not self.dir_in:
@ -2837,6 +3002,24 @@ class Eynollah:
if self.dir_in:
self.reset_file_name_dir(os.path.join(self.dir_in,img_name))
if self.extract_only_images:
img_res, is_image_enhanced, num_col_classifier, num_column_is_classified = self.run_enhancement(self.light_version)
self.logger.info("Enhancing took %.1fs ", time.time() - t0)
text_regions_p_1 ,erosion_hurts, polygons_lines_xml,polygons_of_images,image_page, page_coord, cont_page = self.get_regions_light_v_extract_only_images(img_res, is_image_enhanced, num_col_classifier)
pcgts = self.writer.build_pagexml_no_full_layout([], page_coord, [], [], [], [], polygons_of_images, [], [], [], [], [], cont_page, [], [])
if self.plotter:
self.plotter.write_images_into_directory(polygons_of_images, image_page)
if self.dir_in:
self.writer.write_pagexml(pcgts)
else:
return pcgts
else:
img_res, is_image_enhanced, num_col_classifier, num_column_is_classified = self.run_enhancement(self.light_version)
self.logger.info("Enhancing took %.1fs ", time.time() - t0)
@ -3091,6 +3274,7 @@ class Eynollah:
pcgts = self.writer.build_pagexml_full_layout(contours_only_text_parent, contours_only_text_parent_h, page_coord, order_text_new, id_of_texts_tot, all_found_textline_polygons, all_found_textline_polygons_h, all_box_coord, all_box_coord_h, polygons_of_images, contours_tables, polygons_of_drop_capitals, polygons_of_marginals, all_found_textline_polygons_marginals, all_box_coord_marginals, slopes, slopes_h, slopes_marginals, cont_page, polygons_lines_xml)
self.logger.info("Job done in %.1fs", time.time() - t0)
if not self.dir_in:
return pcgts
else:

6
src/eynollah/ocrd-tool.json
Unescape Escape View File

@ -52,10 +52,10 @@
},
"resources": [
{
"description": "models for eynollah (TensorFlow format)",
"url": "https://github.com/qurator-spk/eynollah/releases/download/v0.3.0/models_eynollah.tar.gz",
"description": "models for eynollah (TensorFlow SavedModel format)",
"url": "https://github.com/qurator-spk/eynollah/releases/download/v0.3.1/models_eynollah.tar.gz",
"name": "default",
"size": 1761991295,
"size": 1894627041,
"type": "archive",
"path_in_archive": "models_eynollah"
}

8
src/eynollah/writer.py
Unescape Escape View File

@ -172,10 +172,18 @@ class EynollahXmlWriter():
page.add_ImageRegion(img_region)
points_co = ''
for lmm in range(len(found_polygons_text_region_img[mm])):
try:
points_co += str(int((found_polygons_text_region_img[mm][lmm,0,0] + page_coord[2]) / self.scale_x))
points_co += ','
points_co += str(int((found_polygons_text_region_img[mm][lmm,0,1] + page_coord[0]) / self.scale_y))
points_co += ' '
except:
points_co += str(int((found_polygons_text_region_img[mm][lmm][0] + page_coord[2])/ self.scale_x ))
points_co += ','
points_co += str(int((found_polygons_text_region_img[mm][lmm][1] + page_coord[0])/ self.scale_y ))
points_co += ' '
img_region.get_Coords().set_points(points_co[:-1])
for mm in range(len(polygons_lines_to_be_written_in_xml)):

Write Preview
Loading…
Cancel
Save