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

first update for only images extraction

Browse Source
pull/132/head
vahidrezanezhad 12 months ago
parent 6018b354aa
commit e7d12d3549
1 changed files with 376 additions and 261 deletions
Show Stats Download Patch File Download Diff File

129
qurator/eynollah/eynollah.py
Unescape Escape View File

@ -195,6 +195,7 @@ class Eynollah:
self.allow_scaling = allow_scaling
self.headers_off = headers_off
self.light_version = light_version
self.extract_only_images = True
self.ignore_page_extraction = ignore_page_extraction
self.pcgts = pcgts
if not dir_in:
@ -225,6 +226,7 @@ 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:
@ -249,7 +251,23 @@ 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)
@ -268,6 +286,7 @@ class Eynollah:
self.ls_imgs = os.listdir(self.dir_in)
def _cache_images(self, image_filename=None, image_pil=None):
ret = {}
if image_filename:
@ -463,6 +482,27 @@ 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:
@ -570,6 +610,7 @@ 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:
@ -581,6 +622,10 @@ class Eynollah:
num_column_is_classified = True
image_res = np.copy(img)
is_image_enhanced = False
else:
img_new, num_column_is_classified = self.calculate_width_height_by_columns_extract_only_images(img, num_col, width_early, label_p_pred)
image_res = np.copy(img_new)
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
@ -867,12 +912,14 @@ 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<1] =0
else:
seg_not_base[seg_not_base>0.03] =1
seg_not_base[seg_not_base<1] =0
seg_test = label_p_pred[0,:,:,1]
##seg2 = -label_p_pred[0,:,:,2]
@ -888,11 +935,8 @@ 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
@ -908,6 +952,7 @@ class Eynollah:
#seg[seg==1]=0
#seg[seg_test==1]=1
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)
@ -1573,6 +1618,60 @@ 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_light_v")
erosion_hurts = False
img_org = np.copy(img)
img_height_h = img_org.shape[0]
img_width_h = img_org.shape[1]
#model_region, session_region = self.start_new_session_and_model(self.model_region_dir_p_ens)
img_resized = np.copy(img)
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 )
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))
polygons_of_images = return_contours_of_interested_region(text_regions_p_true, 2)
return text_regions_p_true, erosion_hurts, polygons_lines_xml, polygons_of_images
def get_regions_light_v(self,img,is_image_enhanced, num_col_classifier):
self.logger.debug("enter get_regions_light_v")
erosion_hurts = False
@ -2825,6 +2924,8 @@ class Eynollah:
"""
self.logger.debug("enter run")
self.extract_only_images = True
t0_tot = time.time()
@ -2836,6 +2937,20 @@ 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 = self.get_regions_light_v_extract_only_images(img_res, is_image_enhanced, num_col_classifier)
#self.logger.info("Textregion detection took %.1fs ", time.time() - t1t)
if self.plotter:
self.plotter.write_images_into_directory(polygons_of_images, img_res)
#plt.imshow(text_regions_p_1)
#plt.show()
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)

Write Preview
Loading…
Cancel
Save