qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-07-04 16:39:56 +02:00
Code Issues Projects Releases Wiki Activity

attempting partial revert of dir_in mode from c606391c31

Browse source
This commit is contained in:
Clemens Neudecker 2024-03-12 14:35:03 +01:00
parent 482511adc0
commit ca6090fef1
3 changed files with 270 additions and 268 deletions
Download patch file Download diff file Expand all files Collapse all files

23
eynollah/eynollah/cli.py
View file

@ -19,12 +19,13 @@ from eynollah.eynollah.eynollah import Eynollah
type=click.Path(exists=True, file_okay=False), type=click.Path(exists=True, file_okay=False),
required=True, required=True,
) )
@click.option( # temporary disable directory input
"--dir_in", # @click.option(
"-di", # "--dir_in",
help="directory of images", # "-di",
type=click.Path(exists=True, file_okay=False), # help="directory of images",
) # type=click.Path(exists=True, file_okay=False),
# )
@click.option( @click.option(
"--model", "--model",
"-m", "-m",
@ -143,7 +144,7 @@ from eynollah.eynollah.eynollah import Eynollah
def main( def main(
image, image,
out, out,
dir_in, # dir_in,
model, model,
save_images, save_images,
save_layout, save_layout,
@ -179,7 +180,7 @@ def main(
eynollah = Eynollah( eynollah = Eynollah(
image_filename=image, image_filename=image,
dir_out=out, dir_out=out,
dir_in=dir_in, # dir_in=dir_in,
dir_models=model, dir_models=model,
dir_of_cropped_images=save_images, dir_of_cropped_images=save_images,
dir_of_layout=save_layout, dir_of_layout=save_layout,
@ -199,9 +200,9 @@ def main(
light_version=light_version, light_version=light_version,
ignore_page_extraction=ignore_page_extraction, ignore_page_extraction=ignore_page_extraction,
) )
eynollah.run() # eynollah.run()
# pcgts = eynollah.run() pcgts = eynollah.run()
# eynollah.writer.write_pagexml(pcgts) eynollah.writer.write_pagexml(pcgts)
if __name__ == "__main__": if __name__ == "__main__":

225
eynollah/eynollah/eynollah.py
View file

@ -145,11 +145,11 @@ class Eynollah:
def __init__( def __init__(
self, self,
dir_models, dir_models,
image_filename=None, image_filename,
image_pil=None, image_pil=None,
image_filename_stem=None, image_filename_stem=None,
dir_out=None, dir_out=None,
dir_in=None, # dir_in=None,
dir_of_cropped_images=None, dir_of_cropped_images=None,
dir_of_layout=None, dir_of_layout=None,
dir_of_deskewed=None, dir_of_deskewed=None,
@ -171,16 +171,16 @@ class Eynollah:
logger=None, logger=None,
pcgts=None, pcgts=None,
): ):
if not dir_in: # if not dir_in:
if image_pil: # if image_pil:
self._imgs = self._cache_images(image_pil=image_pil) # self._imgs = self._cache_images(image_pil=image_pil)
else: # else:
self._imgs = self._cache_images(image_filename=image_filename) # self._imgs = self._cache_images(image_filename=image_filename)
if override_dpi: # if override_dpi:
self.dpi = override_dpi # self.dpi = override_dpi
self.image_filename = image_filename # self.image_filename = image_filename
self.dir_out = dir_out self.dir_out = dir_out
self.dir_in = dir_in # self.dir_in = dir_in
self.dir_of_all = dir_of_all self.dir_of_all = dir_of_all
self.dir_save_page = dir_save_page self.dir_save_page = dir_save_page
self.dir_of_deskewed = dir_of_deskewed self.dir_of_deskewed = dir_of_deskewed
@ -200,7 +200,7 @@ class Eynollah:
self.light_version = light_version self.light_version = light_version
self.ignore_page_extraction = ignore_page_extraction self.ignore_page_extraction = ignore_page_extraction
self.pcgts = pcgts self.pcgts = pcgts
if not dir_in: # if not dir_in:
self.plotter = None if not enable_plotting else EynollahPlotter( self.plotter = None if not enable_plotting else EynollahPlotter(
dir_out=self.dir_out, dir_out=self.dir_out,
dir_of_all=dir_of_all, dir_of_all=dir_of_all,
@ -236,39 +236,39 @@ class Eynollah:
self.models = {} self.models = {}
if dir_in and light_version: # if dir_in and light_version:
config = tf.compat.v1.ConfigProto() # config = tf.compat.v1.ConfigProto()
config.gpu_options.allow_growth = True # config.gpu_options.allow_growth = True
session = tf.compat.v1.Session(config=config) # session = tf.compat.v1.Session(config=config)
set_session(session) # set_session(session)
self.model_page = self.our_load_model(self.model_page_dir) # 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_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_bin = self.our_load_model(self.model_dir_of_binarization)
self.model_textline = self.our_load_model(self.model_textline_dir) # 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) # self.model_region = self.our_load_model(self.model_region_dir_p_ens_light)
self.model_region_fl_np = self.our_load_model(self.model_region_dir_fully_np) # 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.model_region_fl = self.our_load_model(self.model_region_dir_fully)
self.ls_imgs = os.listdir(self.dir_in) # self.ls_imgs = os.listdir(self.dir_in)
if dir_in and not light_version: # if dir_in and not light_version:
config = tf.compat.v1.ConfigProto() # config = tf.compat.v1.ConfigProto()
config.gpu_options.allow_growth = True # config.gpu_options.allow_growth = True
session = tf.compat.v1.Session(config=config) # session = tf.compat.v1.Session(config=config)
set_session(session) # set_session(session)
self.model_page = self.our_load_model(self.model_page_dir) # 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_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_bin = self.our_load_model(self.model_dir_of_binarization)
self.model_textline = self.our_load_model(self.model_textline_dir) # self.model_textline = self.our_load_model(self.model_textline_dir)
self.model_region = self.our_load_model(self.model_region_dir_p_ens) # self.model_region = self.our_load_model(self.model_region_dir_p_ens)
self.model_region_p2 = self.our_load_model(self.model_region_dir_p2) # self.model_region_p2 = self.our_load_model(self.model_region_dir_p2)
self.model_region_fl_np = self.our_load_model(self.model_region_dir_fully_np) # 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.model_region_fl = self.our_load_model(self.model_region_dir_fully)
self.model_enhancement = self.our_load_model(self.model_dir_of_enhancement) # self.model_enhancement = self.our_load_model(self.model_dir_of_enhancement)
self.ls_imgs = os.listdir(self.dir_in) # self.ls_imgs = os.listdir(self.dir_in)
def _cache_images(self, image_filename=None, image_pil=None): def _cache_images(self, image_filename=None, image_pil=None):
ret = {} ret = {}
@ -283,9 +283,9 @@ class Eynollah:
ret[f'img{prefix}_uint8'] = ret[f'img{prefix}'].astype(np.uint8) ret[f'img{prefix}_uint8'] = ret[f'img{prefix}'].astype(np.uint8)
return ret return ret
def reset_file_name_dir(self, image_filename): # def reset_file_name_dir(self, image_filename):
self._imgs = self._cache_images(image_filename=image_filename) # self._imgs = self._cache_images(image_filename=image_filename)
self.image_filename = image_filename # self.image_filename = image_filename
self.plotter = None if not self.enable_plotting else EynollahPlotter( self.plotter = None if not self.enable_plotting else EynollahPlotter(
dir_out=self.dir_out, dir_out=self.dir_out,
@ -476,7 +476,7 @@ class Eynollah:
img = self.imread() img = self.imread()
_, page_coord = self.early_page_for_num_of_column_classification(img) _, page_coord = self.early_page_for_num_of_column_classification(img)
if not self.dir_in: # if not self.dir_in:
model_num_classifier, session_col_classifier = self.start_new_session_and_model( model_num_classifier, session_col_classifier = self.start_new_session_and_model(
self.model_dir_of_col_classifier) self.model_dir_of_col_classifier)
if self.input_binary: if self.input_binary:
@ -501,10 +501,10 @@ class Eynollah:
img_in[0, :, :, 1] = img_1ch[:, :] img_in[0, :, :, 1] = img_1ch[:, :]
img_in[0, :, :, 2] = img_1ch[:, :] img_in[0, :, :, 2] = img_1ch[:, :]
if not self.dir_in: # if not self.dir_in:
label_p_pred = model_num_classifier.predict(img_in, verbose=0) label_p_pred = model_num_classifier.predict(img_in, verbose=0)
else: # else:
label_p_pred = self.model_classifier.predict(img_in, verbose=0) # label_p_pred = self.model_classifier.predict(img_in, verbose=0)
num_col = np.argmax(label_p_pred[0]) + 1 num_col = np.argmax(label_p_pred[0]) + 1
@ -524,9 +524,9 @@ class Eynollah:
self.logger.info("Detected %s DPI", dpi) self.logger.info("Detected %s DPI", dpi)
if self.input_binary: if self.input_binary:
img = self.imread() img = self.imread()
if self.dir_in: # if self.dir_in:
prediction_bin = self.do_prediction(True, img, self.model_bin) # prediction_bin = self.do_prediction(True, img, self.model_bin)
else: # else:
model_bin, session_bin = self.start_new_session_and_model(self.model_dir_of_binarization) model_bin, session_bin = self.start_new_session_and_model(self.model_dir_of_binarization)
prediction_bin = self.do_prediction(True, img, model_bin) prediction_bin = self.do_prediction(True, img, model_bin)
@ -546,7 +546,7 @@ class Eynollah:
t1 = time.time() t1 = time.time()
_, page_coord = self.early_page_for_num_of_column_classification(img_bin) _, page_coord = self.early_page_for_num_of_column_classification(img_bin)
if not self.dir_in: # if not self.dir_in:
model_num_classifier, session_col_classifier = self.start_new_session_and_model( model_num_classifier, session_col_classifier = self.start_new_session_and_model(
self.model_dir_of_col_classifier) self.model_dir_of_col_classifier)
@ -568,9 +568,10 @@ class Eynollah:
img_in[0, :, :, 1] = img_1ch[:, :] img_in[0, :, :, 1] = img_1ch[:, :]
img_in[0, :, :, 2] = img_1ch[:, :] img_in[0, :, :, 2] = img_1ch[:, :]
if self.dir_in: # if self.dir_in:
label_p_pred = self.model_classifier.predict(img_in, verbose=0) # label_p_pred = self.model_classifier.predict(img_in, verbose=0)
else: # else:
# label_p_pred = model_num_classifier.predict(img_in, verbose=0)
label_p_pred = model_num_classifier.predict(img_in, verbose=0) label_p_pred = model_num_classifier.predict(img_in, verbose=0)
num_col = np.argmax(label_p_pred[0]) + 1 num_col = np.argmax(label_p_pred[0]) + 1
@ -984,13 +985,13 @@ class Eynollah:
if not self.ignore_page_extraction: if not self.ignore_page_extraction:
img = cv2.GaussianBlur(self.image, (5, 5), 0) img = cv2.GaussianBlur(self.image, (5, 5), 0)
if not self.dir_in: # if not self.dir_in:
model_page, session_page = self.start_new_session_and_model(self.model_page_dir) model_page, session_page = self.start_new_session_and_model(self.model_page_dir)
if not self.dir_in: # if not self.dir_in:
img_page_prediction = self.do_prediction(False, img, model_page) img_page_prediction = self.do_prediction(False, img, model_page)
else: # else:
img_page_prediction = self.do_prediction(False, img, self.model_page) # img_page_prediction = self.do_prediction(False, img, self.model_page)
imgray = cv2.cvtColor(img_page_prediction, cv2.COLOR_BGR2GRAY) imgray = cv2.cvtColor(img_page_prediction, cv2.COLOR_BGR2GRAY)
_, thresh = cv2.threshold(imgray, 0, 255, 0) _, thresh = cv2.threshold(imgray, 0, 255, 0)
thresh = cv2.dilate(thresh, KERNEL, iterations=3) thresh = cv2.dilate(thresh, KERNEL, iterations=3)
@ -1036,13 +1037,13 @@ class Eynollah:
img = img.astype(np.uint8) img = img.astype(np.uint8)
else: else:
img = self.imread() img = self.imread()
if not self.dir_in: # if not self.dir_in:
model_page, session_page = self.start_new_session_and_model(self.model_page_dir) model_page, session_page = self.start_new_session_and_model(self.model_page_dir)
img = cv2.GaussianBlur(img, (5, 5), 0) img = cv2.GaussianBlur(img, (5, 5), 0)
if self.dir_in: # if self.dir_in:
img_page_prediction = self.do_prediction(False, img, self.model_page) # img_page_prediction = self.do_prediction(False, img, self.model_page)
else: # else:
img_page_prediction = self.do_prediction(False, img, model_page) img_page_prediction = self.do_prediction(False, img, model_page)
imgray = cv2.cvtColor(img_page_prediction, cv2.COLOR_BGR2GRAY) imgray = cv2.cvtColor(img_page_prediction, cv2.COLOR_BGR2GRAY)
@ -1069,11 +1070,11 @@ class Eynollah:
self.logger.debug("enter extract_text_regions") self.logger.debug("enter extract_text_regions")
img_height_h = img.shape[0] img_height_h = img.shape[0]
img_width_h = img.shape[1] img_width_h = img.shape[1]
if not self.dir_in: # if not self.dir_in:
model_region, session_region = self.start_new_session_and_model( model_region, session_region = self.start_new_session_and_model(
self.model_region_dir_fully if patches else self.model_region_dir_fully_np) self.model_region_dir_fully if patches else self.model_region_dir_fully_np)
else: # else:
model_region = self.model_region_fl if patches else self.model_region_fl_np # model_region = self.model_region_fl if patches else self.model_region_fl_np
if not patches: if not patches:
img = otsu_copy_binary(img) img = otsu_copy_binary(img)
@ -1588,7 +1589,7 @@ class Eynollah:
def textline_contours(self, img, patches, scaler_h, scaler_w): def textline_contours(self, img, patches, scaler_h, scaler_w):
self.logger.debug('enter textline_contours') self.logger.debug('enter textline_contours')
if not self.dir_in: # if not self.dir_in:
model_textline, session_textline = self.start_new_session_and_model( model_textline, session_textline = self.start_new_session_and_model(
self.model_textline_dir if patches else self.model_textline_dir_np) self.model_textline_dir if patches else self.model_textline_dir_np)
img = img.astype(np.uint8) img = img.astype(np.uint8)
@ -1596,15 +1597,15 @@ class Eynollah:
img_h = img_org.shape[0] img_h = img_org.shape[0]
img_w = img_org.shape[1] img_w = img_org.shape[1]
img = resize_image(img_org, int(img_org.shape[0] * scaler_h), int(img_org.shape[1] * scaler_w)) img = resize_image(img_org, int(img_org.shape[0] * scaler_h), int(img_org.shape[1] * scaler_w))
if not self.dir_in: # if not self.dir_in:
prediction_textline = self.do_prediction(patches, img, model_textline) prediction_textline = self.do_prediction(patches, img, model_textline)
else: # else:
prediction_textline = self.do_prediction(patches, img, self.model_textline) # prediction_textline = self.do_prediction(patches, img, self.model_textline)
prediction_textline = resize_image(prediction_textline, img_h, img_w) prediction_textline = resize_image(prediction_textline, img_h, img_w)
if not self.dir_in: # if not self.dir_in:
prediction_textline_longshot = self.do_prediction(False, img, model_textline) prediction_textline_longshot = self.do_prediction(False, img, model_textline)
else: # else:
prediction_textline_longshot = self.do_prediction(False, img, self.model_textline) # prediction_textline_longshot = self.do_prediction(False, img, self.model_textline)
prediction_textline_longshot_true_size = resize_image(prediction_textline_longshot, img_h, img_w) prediction_textline_longshot_true_size = resize_image(prediction_textline_longshot, img_h, img_w)
if self.textline_light: if self.textline_light:
@ -1681,11 +1682,11 @@ class Eynollah:
img_h_new = int(img_org.shape[0] / float(img_org.shape[1]) * img_w_new) img_h_new = int(img_org.shape[0] / float(img_org.shape[1]) * img_w_new)
img_resized = resize_image(img, img_h_new, img_w_new) img_resized = resize_image(img, img_h_new, img_w_new)
if not self.dir_in: # if not self.dir_in:
model_bin, session_bin = self.start_new_session_and_model(self.model_dir_of_binarization) model_bin, session_bin = self.start_new_session_and_model(self.model_dir_of_binarization)
prediction_bin = self.do_prediction(True, img_resized, model_bin) prediction_bin = self.do_prediction(True, img_resized, model_bin)
else: # else:
prediction_bin = self.do_prediction(True, img_resized, self.model_bin) # prediction_bin = self.do_prediction(True, img_resized, self.model_bin)
prediction_bin = prediction_bin[:, :, 0] prediction_bin = prediction_bin[:, :, 0]
prediction_bin = (prediction_bin[:, :] == 0) * 1 prediction_bin = (prediction_bin[:, :] == 0) * 1
prediction_bin = prediction_bin * 255 prediction_bin = prediction_bin * 255
@ -1698,11 +1699,11 @@ class Eynollah:
textline_mask_tot_ea = self.run_textline(img_bin) textline_mask_tot_ea = self.run_textline(img_bin)
if not self.dir_in: # if not self.dir_in:
model_region, session_region = self.start_new_session_and_model(self.model_region_dir_p_ens_light) model_region, session_region = self.start_new_session_and_model(self.model_region_dir_p_ens_light)
prediction_regions_org = self.do_prediction_new_concept(True, img_bin, model_region) prediction_regions_org = self.do_prediction_new_concept(True, img_bin, model_region)
else: # else:
prediction_regions_org = self.do_prediction_new_concept(True, img_bin, self.model_region) # prediction_regions_org = self.do_prediction_new_concept(True, img_bin, self.model_region)
# plt.imshow(prediction_regions_org[:,:,0]) # plt.imshow(prediction_regions_org[:,:,0])
# plt.show() # plt.show()
@ -1744,17 +1745,17 @@ class Eynollah:
img_height_h = img_org.shape[0] img_height_h = img_org.shape[0]
img_width_h = img_org.shape[1] img_width_h = img_org.shape[1]
if not self.dir_in: # if not self.dir_in:
model_region, session_region = self.start_new_session_and_model(self.model_region_dir_p_ens) model_region, session_region = self.start_new_session_and_model(self.model_region_dir_p_ens)
ratio_y = 1.3 ratio_y = 1.3
ratio_x = 1 ratio_x = 1
img = resize_image(img_org, int(img_org.shape[0] * ratio_y), int(img_org.shape[1] * ratio_x)) img = resize_image(img_org, int(img_org.shape[0] * ratio_y), int(img_org.shape[1] * ratio_x))
if not self.dir_in: # if not self.dir_in:
prediction_regions_org_y = self.do_prediction(True, img, model_region) prediction_regions_org_y = self.do_prediction(True, img, model_region)
else: # else:
prediction_regions_org_y = self.do_prediction(True, img, self.model_region) # prediction_regions_org_y = self.do_prediction(True, img, self.model_region)
prediction_regions_org_y = resize_image(prediction_regions_org_y, img_height_h, img_width_h) prediction_regions_org_y = resize_image(prediction_regions_org_y, img_height_h, img_width_h)
# plt.imshow(prediction_regions_org_y[:,:,0]) # plt.imshow(prediction_regions_org_y[:,:,0])
@ -1774,23 +1775,23 @@ class Eynollah:
img = resize_image(img_org, int(img_org.shape[0]), img = resize_image(img_org, int(img_org.shape[0]),
int(img_org.shape[1] * (1.2 if is_image_enhanced else 1))) int(img_org.shape[1] * (1.2 if is_image_enhanced else 1)))
if self.dir_in: # if self.dir_in:
prediction_regions_org = self.do_prediction(True, img, self.model_region) # prediction_regions_org = self.do_prediction(True, img, self.model_region)
else: # else:
prediction_regions_org = self.do_prediction(True, img, model_region) prediction_regions_org = self.do_prediction(True, img, model_region)
prediction_regions_org = resize_image(prediction_regions_org, img_height_h, img_width_h) 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[:, :, 0]
prediction_regions_org[(prediction_regions_org[:, :] == 1) & (mask_zeros_y[:, :] == 1)] = 0 prediction_regions_org[(prediction_regions_org[:, :] == 1) & (mask_zeros_y[:, :] == 1)] = 0
if not self.dir_in: # if not self.dir_in:
model_region, session_region = self.start_new_session_and_model(self.model_region_dir_p2) model_region, session_region = self.start_new_session_and_model(self.model_region_dir_p2)
img = resize_image(img_org, int(img_org.shape[0]), int(img_org.shape[1])) img = resize_image(img_org, int(img_org.shape[0]), int(img_org.shape[1]))
if self.dir_in: # if self.dir_in:
prediction_regions_org2 = self.do_prediction(True, img, self.model_region_p2, 0.2) # prediction_regions_org2 = self.do_prediction(True, img, self.model_region_p2, 0.2)
else: # else:
prediction_regions_org2 = self.do_prediction(True, img, model_region, 0.2) prediction_regions_org2 = self.do_prediction(True, img, model_region, 0.2)
prediction_regions_org2 = resize_image(prediction_regions_org2, img_height_h, img_width_h) prediction_regions_org2 = resize_image(prediction_regions_org2, img_height_h, img_width_h)
@ -1817,11 +1818,11 @@ class Eynollah:
if self.input_binary: if self.input_binary:
prediction_bin = np.copy(img_org) prediction_bin = np.copy(img_org)
else: else:
if not self.dir_in: # if not self.dir_in:
model_bin, session_bin = self.start_new_session_and_model(self.model_dir_of_binarization) model_bin, session_bin = self.start_new_session_and_model(self.model_dir_of_binarization)
prediction_bin = self.do_prediction(True, img_org, model_bin) prediction_bin = self.do_prediction(True, img_org, model_bin)
else: # else:
prediction_bin = self.do_prediction(True, img_org, self.model_bin) # prediction_bin = self.do_prediction(True, img_org, self.model_bin)
prediction_bin = resize_image(prediction_bin, img_height_h, img_width_h) prediction_bin = resize_image(prediction_bin, img_height_h, img_width_h)
prediction_bin = prediction_bin[:, :, 0] prediction_bin = prediction_bin[:, :, 0]
@ -1830,17 +1831,17 @@ class Eynollah:
prediction_bin = np.repeat(prediction_bin[:, :, np.newaxis], 3, axis=2) prediction_bin = np.repeat(prediction_bin[:, :, np.newaxis], 3, axis=2)
if not self.dir_in: # if not self.dir_in:
model_region, session_region = self.start_new_session_and_model(self.model_region_dir_p_ens) model_region, session_region = self.start_new_session_and_model(self.model_region_dir_p_ens)
ratio_y = 1 ratio_y = 1
ratio_x = 1 ratio_x = 1
img = resize_image(prediction_bin, int(img_org.shape[0] * ratio_y), int(img_org.shape[1] * ratio_x)) img = resize_image(prediction_bin, int(img_org.shape[0] * ratio_y), int(img_org.shape[1] * ratio_x))
if not self.dir_in: # if not self.dir_in:
prediction_regions_org = self.do_prediction(True, img, model_region) prediction_regions_org = self.do_prediction(True, img, model_region)
else: # else:
prediction_regions_org = self.do_prediction(True, img, self.model_region) # prediction_regions_org = self.do_prediction(True, img, self.model_region)
prediction_regions_org = resize_image(prediction_regions_org, img_height_h, img_width_h) 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[:, :, 0]
@ -1869,11 +1870,11 @@ class Eynollah:
if self.input_binary: if self.input_binary:
prediction_bin = np.copy(img_org) prediction_bin = np.copy(img_org)
if not self.dir_in: # if not self.dir_in:
model_bin, session_bin = self.start_new_session_and_model(self.model_dir_of_binarization) model_bin, session_bin = self.start_new_session_and_model(self.model_dir_of_binarization)
prediction_bin = self.do_prediction(True, img_org, model_bin) prediction_bin = self.do_prediction(True, img_org, model_bin)
else: # else:
prediction_bin = self.do_prediction(True, img_org, self.model_bin) # prediction_bin = self.do_prediction(True, img_org, self.model_bin)
prediction_bin = resize_image(prediction_bin, img_height_h, img_width_h) prediction_bin = resize_image(prediction_bin, img_height_h, img_width_h)
prediction_bin = prediction_bin[:, :, 0] prediction_bin = prediction_bin[:, :, 0]
@ -1883,7 +1884,7 @@ class Eynollah:
prediction_bin = np.repeat(prediction_bin[:, :, np.newaxis], 3, axis=2) prediction_bin = np.repeat(prediction_bin[:, :, np.newaxis], 3, axis=2)
if not self.dir_in: # if not self.dir_in:
model_region, session_region = self.start_new_session_and_model(self.model_region_dir_p_ens) model_region, session_region = self.start_new_session_and_model(self.model_region_dir_p_ens)
else: else:
@ -1892,10 +1893,10 @@ class Eynollah:
ratio_x = 1 ratio_x = 1
img = resize_image(prediction_bin, int(img_org.shape[0] * ratio_y), int(img_org.shape[1] * ratio_x)) img = resize_image(prediction_bin, int(img_org.shape[0] * ratio_y), int(img_org.shape[1] * ratio_x))
if not self.dir_in: # if not self.dir_in:
prediction_regions_org = self.do_prediction(True, img, model_region) prediction_regions_org = self.do_prediction(True, img, model_region)
else: # else:
prediction_regions_org = self.do_prediction(True, img, self.model_region) # prediction_regions_org = self.do_prediction(True, img, self.model_region)
prediction_regions_org = resize_image(prediction_regions_org, img_height_h, img_width_h) 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[:, :, 0]
@ -3036,13 +3037,13 @@ class Eynollah:
t0_tot = time.time() t0_tot = time.time()
if not self.dir_in: # if not self.dir_in:
self.ls_imgs = [1] self.ls_imgs = [1]
for img_name in self.ls_imgs: for img_name in self.ls_imgs:
t0 = time.time() t0 = time.time()
if self.dir_in: # if self.dir_in:
self.reset_file_name_dir(os.path.join(self.dir_in, img_name)) # self.reset_file_name_dir(os.path.join(self.dir_in, img_name))
img_res, is_image_enhanced, num_col_classifier, num_column_is_classified = self.run_enhancement( img_res, is_image_enhanced, num_col_classifier, num_column_is_classified = self.run_enhancement(
self.light_version) self.light_version)
@ -3077,10 +3078,10 @@ class Eynollah:
pcgts = self.writer.build_pagexml_no_full_layout([], page_coord, [], [], [], [], [], [], [], [], [], [], pcgts = self.writer.build_pagexml_no_full_layout([], page_coord, [], [], [], [], [], [], [], [], [], [],
cont_page, [], []) cont_page, [], [])
self.logger.info("Job done in %.1fs", time.time() - t1) self.logger.info("Job done in %.1fs", time.time() - t1)
if self.dir_in: # if self.dir_in:
self.writer.write_pagexml(pcgts) # self.writer.write_pagexml(pcgts)
continue # continue
else: # else:
return pcgts return pcgts
t1 = time.time() t1 = time.time()
@ -3419,5 +3420,5 @@ class Eynollah:
# return pcgts # return pcgts
self.writer.write_pagexml(pcgts) self.writer.write_pagexml(pcgts)
# self.logger.info("Job done in %.1fs", time.time() - t0) # self.logger.info("Job done in %.1fs", time.time() - t0)
if self.dir_in: # if self.dir_in:
self.logger.info("All jobs done in %.1fs", time.time() - t0_tot) # self.logger.info("All jobs done in %.1fs", time.time() - t0_tot)

190
eynollah/eynollah/utils/contour.py
View file

@ -3,8 +3,8 @@ import numpy as np
from shapely import geometry from shapely import geometry
from .rotate import rotate_image, rotation_image_new from .rotate import rotate_image, rotation_image_new
from multiprocessing import Process, Queue, cpu_count # from multiprocessing import Process, Queue, cpu_count
from multiprocessing import Pool # from multiprocessing import Pool
def contours_in_same_horizon(cy_main_hor): def contours_in_same_horizon(cy_main_hor):
@ -154,95 +154,95 @@ def return_contours_of_interested_region(region_pre_p, pixel, min_area=0.0002):
return contours_imgs return contours_imgs
def do_work_of_contours_in_image(queue_of_all_params, contours_per_process, indexes_r_con_per_pro, img, slope_first): # def do_work_of_contours_in_image(queue_of_all_params, contours_per_process, indexes_r_con_per_pro, img, slope_first):
cnts_org_per_each_subprocess = [] # cnts_org_per_each_subprocess = []
index_by_text_region_contours = [] # index_by_text_region_contours = []
for mv in range(len(contours_per_process)): # for mv in range(len(contours_per_process)):
index_by_text_region_contours.append(indexes_r_con_per_pro[mv]) # index_by_text_region_contours.append(indexes_r_con_per_pro[mv])
img_copy = np.zeros(img.shape) # img_copy = np.zeros(img.shape)
img_copy = cv2.fillPoly(img_copy, pts=[contours_per_process[mv]], color=(1, 1, 1)) # img_copy = cv2.fillPoly(img_copy, pts=[contours_per_process[mv]], color=(1, 1, 1))
img_copy = rotation_image_new(img_copy, -slope_first) # img_copy = rotation_image_new(img_copy, -slope_first)
img_copy = img_copy.astype(np.uint8) # img_copy = img_copy.astype(np.uint8)
imgray = cv2.cvtColor(img_copy, cv2.COLOR_BGR2GRAY) # imgray = cv2.cvtColor(img_copy, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0) # ret, thresh = cv2.threshold(imgray, 0, 255, 0)
cont_int, _ = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) # cont_int, _ = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cont_int[0][:, 0, 0] = cont_int[0][:, 0, 0] + np.abs(img_copy.shape[1] - img.shape[1]) # cont_int[0][:, 0, 0] = cont_int[0][:, 0, 0] + np.abs(img_copy.shape[1] - img.shape[1])
cont_int[0][:, 0, 1] = cont_int[0][:, 0, 1] + np.abs(img_copy.shape[0] - img.shape[0]) # cont_int[0][:, 0, 1] = cont_int[0][:, 0, 1] + np.abs(img_copy.shape[0] - img.shape[0])
cnts_org_per_each_subprocess.append(cont_int[0]) # cnts_org_per_each_subprocess.append(cont_int[0])
queue_of_all_params.put([cnts_org_per_each_subprocess, index_by_text_region_contours]) # queue_of_all_params.put([cnts_org_per_each_subprocess, index_by_text_region_contours])
def get_textregion_contours_in_org_image_multi(cnts, img, slope_first): # def get_textregion_contours_in_org_image_multi(cnts, img, slope_first):
num_cores = cpu_count() # num_cores = cpu_count()
queue_of_all_params = Queue() # queue_of_all_params = Queue()
processes = [] # processes = []
nh = np.linspace(0, len(cnts), num_cores + 1) # nh = np.linspace(0, len(cnts), num_cores + 1)
indexes_by_text_con = np.array(range(len(cnts))) # indexes_by_text_con = np.array(range(len(cnts)))
for i in range(num_cores): # for i in range(num_cores):
contours_per_process = cnts[int(nh[i]): int(nh[i + 1])] # contours_per_process = cnts[int(nh[i]): int(nh[i + 1])]
indexes_text_con_per_process = indexes_by_text_con[int(nh[i]): int(nh[i + 1])] # indexes_text_con_per_process = indexes_by_text_con[int(nh[i]): int(nh[i + 1])]
processes.append(Process(target=do_work_of_contours_in_image, args=(queue_of_all_params, contours_per_process, indexes_text_con_per_process, img, slope_first))) # processes.append(Process(target=do_work_of_contours_in_image, args=(queue_of_all_params, contours_per_process, indexes_text_con_per_process, img, slope_first)))
for i in range(num_cores): # for i in range(num_cores):
processes[i].start() # processes[i].start()
cnts_org = [] # cnts_org = []
all_index_text_con = [] # all_index_text_con = []
for i in range(num_cores): # for i in range(num_cores):
list_all_par = queue_of_all_params.get(True) # list_all_par = queue_of_all_params.get(True)
contours_for_sub_process = list_all_par[0] # contours_for_sub_process = list_all_par[0]
indexes_for_sub_process = list_all_par[1] # indexes_for_sub_process = list_all_par[1]
for j in range(len(contours_for_sub_process)): # for j in range(len(contours_for_sub_process)):
cnts_org.append(contours_for_sub_process[j]) # cnts_org.append(contours_for_sub_process[j])
all_index_text_con.append(indexes_for_sub_process[j]) # all_index_text_con.append(indexes_for_sub_process[j])
for i in range(num_cores): # for i in range(num_cores):
processes[i].join() # processes[i].join()
print(all_index_text_con) # print(all_index_text_con)
return cnts_org # return cnts_org
def loop_contour_image(index_l, cnts, img, slope_first): # def loop_contour_image(index_l, cnts, img, slope_first):
img_copy = np.zeros(img.shape) # img_copy = np.zeros(img.shape)
img_copy = cv2.fillPoly(img_copy, pts=[cnts[index_l]], color=(1, 1, 1)) # img_copy = cv2.fillPoly(img_copy, pts=[cnts[index_l]], color=(1, 1, 1))
# plt.imshow(img_copy) # # plt.imshow(img_copy)
# plt.show() # # plt.show()
# print(img.shape,'img') # # print(img.shape,'img')
img_copy = rotation_image_new(img_copy, -slope_first) # img_copy = rotation_image_new(img_copy, -slope_first)
# print(img_copy.shape,'img_copy') # # print(img_copy.shape,'img_copy')
# plt.imshow(img_copy) # # plt.imshow(img_copy)
# plt.show() # # plt.show()
img_copy = img_copy.astype(np.uint8) # img_copy = img_copy.astype(np.uint8)
imgray = cv2.cvtColor(img_copy, cv2.COLOR_BGR2GRAY) # imgray = cv2.cvtColor(img_copy, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0) # ret, thresh = cv2.threshold(imgray, 0, 255, 0)
cont_int, _ = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) # cont_int, _ = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cont_int[0][:, 0, 0] = cont_int[0][:, 0, 0] + np.abs(img_copy.shape[1] - img.shape[1]) # cont_int[0][:, 0, 0] = cont_int[0][:, 0, 0] + np.abs(img_copy.shape[1] - img.shape[1])
cont_int[0][:, 0, 1] = cont_int[0][:, 0, 1] + np.abs(img_copy.shape[0] - img.shape[0]) # cont_int[0][:, 0, 1] = cont_int[0][:, 0, 1] + np.abs(img_copy.shape[0] - img.shape[0])
# print(np.shape(cont_int[0])) # # print(np.shape(cont_int[0]))
return cont_int[0] # return cont_int[0]
def get_textregion_contours_in_org_image_multi2(cnts, img, slope_first): # def get_textregion_contours_in_org_image_multi2(cnts, img, slope_first):
cnts_org = [] # cnts_org = []
# print(cnts,'cnts') # # print(cnts,'cnts')
with Pool(cpu_count()) as p: # with Pool(cpu_count()) as p:
cnts_org = p.starmap(loop_contour_image, [(index_l, cnts, img, slope_first) for index_l in range(len(cnts))]) # cnts_org = p.starmap(loop_contour_image, [(index_l, cnts, img, slope_first) for index_l in range(len(cnts))])
return cnts_org # return cnts_org
def get_textregion_contours_in_org_image(cnts, img, slope_first): def get_textregion_contours_in_org_image(cnts, img, slope_first):
@ -276,42 +276,42 @@ def get_textregion_contours_in_org_image(cnts, img, slope_first):
return cnts_org return cnts_org
def get_textregion_contours_in_org_image_light(cnts, img, slope_first): # def get_textregion_contours_in_org_image_light(cnts, img, slope_first):
h_o = img.shape[0] # h_o = img.shape[0]
w_o = img.shape[1] # w_o = img.shape[1]
img = cv2.resize(img, (int(img.shape[1]/3.), int(img.shape[0]/3.)), interpolation=cv2.INTER_NEAREST) # img = cv2.resize(img, (int(img.shape[1]/3.), int(img.shape[0]/3.)), interpolation=cv2.INTER_NEAREST)
# cnts = list( (np.array(cnts)/2).astype(np.int16) ) # # cnts = list( (np.array(cnts)/2).astype(np.int16) )
# cnts = cnts/2 # # cnts = cnts/2
cnts = [(i / 3).astype(np.int32) for i in cnts] # cnts = [(i / 3).astype(np.int32) for i in cnts]
cnts_org = [] # cnts_org = []
# print(cnts,'cnts') # # print(cnts,'cnts')
for i in range(len(cnts)): # for i in range(len(cnts)):
img_copy = np.zeros(img.shape) # img_copy = np.zeros(img.shape)
img_copy = cv2.fillPoly(img_copy, pts=[cnts[i]], color=(1, 1, 1)) # img_copy = cv2.fillPoly(img_copy, pts=[cnts[i]], color=(1, 1, 1))
# plt.imshow(img_copy) # # plt.imshow(img_copy)
# plt.show() # # plt.show()
# print(img.shape,'img') # # print(img.shape,'img')
img_copy = rotation_image_new(img_copy, -slope_first) # img_copy = rotation_image_new(img_copy, -slope_first)
# print(img_copy.shape,'img_copy') # # print(img_copy.shape,'img_copy')
# plt.imshow(img_copy) # # plt.imshow(img_copy)
# plt.show() # # plt.show()
img_copy = img_copy.astype(np.uint8) # img_copy = img_copy.astype(np.uint8)
imgray = cv2.cvtColor(img_copy, cv2.COLOR_BGR2GRAY) # imgray = cv2.cvtColor(img_copy, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0) # ret, thresh = cv2.threshold(imgray, 0, 255, 0)
cont_int, _ = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) # cont_int, _ = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cont_int[0][:, 0, 0] = cont_int[0][:, 0, 0] + np.abs(img_copy.shape[1] - img.shape[1]) # cont_int[0][:, 0, 0] = cont_int[0][:, 0, 0] + np.abs(img_copy.shape[1] - img.shape[1])
cont_int[0][:, 0, 1] = cont_int[0][:, 0, 1] + np.abs(img_copy.shape[0] - img.shape[0]) # cont_int[0][:, 0, 1] = cont_int[0][:, 0, 1] + np.abs(img_copy.shape[0] - img.shape[0])
# print(np.shape(cont_int[0])) # # print(np.shape(cont_int[0]))
cnts_org.append(cont_int[0]*3) # cnts_org.append(cont_int[0]*3)
return cnts_org # return cnts_org
def return_contours_of_interested_textline(region_pre_p, pixel): def return_contours_of_interested_textline(region_pre_p, pixel):