qurator-spk/sbb_binarization
1
0
Fork 0
mirror of https://github.com/qurator-spk/sbb_binarization.git synced 2025-07-04 00:19:53 +02:00
Code Issues Releases Wiki Activity

issue #45 the patches option is omitted and it means that documents will be processed in patches while no patches is not desired by the tool

Browse source
This commit is contained in:
vahid 2022-10-11 19:18:40 +02:00
parent eff7a47852
commit 7c3f2176f7
3 changed files with 125 additions and 142 deletions
Download patch file Download diff file Expand all files Collapse all files

5
sbb_binarize/cli.py
View file

@ -7,9 +7,8 @@ from .sbb_binarize import SbbBinarizer
@command() @command()
@version_option() @version_option()
@option('--patches/--no-patches', default=True, help='by enabling this parameter you let the model to see the image in patches.')
@option('--model-dir', '-m', type=types.Path(exists=True, file_okay=False), required=True, help='directory containing models for prediction') @option('--model-dir', '-m', type=types.Path(exists=True, file_okay=False), required=True, help='directory containing models for prediction')
@argument('input_image') @argument('input_image')
@argument('output_image') @argument('output_image')
def main(patches, model_dir, input_image, output_image): def main(model_dir, input_image, output_image):
SbbBinarizer(model_dir).run(image_path=input_image, use_patches=patches, save=output_image) SbbBinarizer(model_dir).run(image_path=input_image, save=output_image)

6
sbb_binarize/ocrd_cli.py
View file

@ -110,7 +110,7 @@ class SbbBinarizeProcessor(Processor):
if oplevel == 'page': if oplevel == 'page':
LOG.info("Binarizing on 'page' level in page '%s'", page_id) LOG.info("Binarizing on 'page' level in page '%s'", page_id)
bin_image = cv2pil(self.binarizer.run(image=pil2cv(page_image), use_patches=True)) bin_image = cv2pil(self.binarizer.run(image=pil2cv(page_image)))
# update METS (add the image file): # update METS (add the image file):
bin_image_path = self.workspace.save_image_file(bin_image, bin_image_path = self.workspace.save_image_file(bin_image,
file_id + '.IMG-BIN', file_id + '.IMG-BIN',
@ -124,7 +124,7 @@ class SbbBinarizeProcessor(Processor):
LOG.warning("Page '%s' contains no text/table regions", page_id) LOG.warning("Page '%s' contains no text/table regions", page_id)
for region in regions: for region in regions:
region_image, region_xywh = self.workspace.image_from_segment(region, page_image, page_xywh, feature_filter='binarized') region_image, region_xywh = self.workspace.image_from_segment(region, page_image, page_xywh, feature_filter='binarized')
region_image_bin = cv2pil(binarizer.run(image=pil2cv(region_image), use_patches=True)) region_image_bin = cv2pil(binarizer.run(image=pil2cv(region_image)))
region_image_bin_path = self.workspace.save_image_file( region_image_bin_path = self.workspace.save_image_file(
region_image_bin, region_image_bin,
"%s_%s.IMG-BIN" % (file_id, region.id), "%s_%s.IMG-BIN" % (file_id, region.id),
@ -139,7 +139,7 @@ class SbbBinarizeProcessor(Processor):
LOG.warning("Page '%s' contains no text lines", page_id) LOG.warning("Page '%s' contains no text lines", page_id)
for region_id, line in region_line_tuples: for region_id, line in region_line_tuples:
line_image, line_xywh = self.workspace.image_from_segment(line, page_image, page_xywh, feature_filter='binarized') line_image, line_xywh = self.workspace.image_from_segment(line, page_image, page_xywh, feature_filter='binarized')
line_image_bin = cv2pil(binarizer.run(image=pil2cv(line_image), use_patches=True)) line_image_bin = cv2pil(binarizer.run(image=pil2cv(line_image)))
line_image_bin_path = self.workspace.save_image_file( line_image_bin_path = self.workspace.save_image_file(
line_image_bin, line_image_bin,
"%s_%s_%s.IMG-BIN" % (file_id, region_id, line.id), "%s_%s_%s.IMG-BIN" % (file_id, region_id, line.id),

22
sbb_binarize/sbb_binarize.py
View file

@ -62,7 +62,7 @@ class SbbBinarizer:
n_classes = model.layers[len(model.layers)-1].output_shape[3] n_classes = model.layers[len(model.layers)-1].output_shape[3]
return model, model_height, model_width, n_classes return model, model_height, model_width, n_classes
def predict(self, model_in, img, use_patches): def predict(self, model_in, img):
tensorflow_backend.set_session(self.session) tensorflow_backend.set_session(self.session)
model, model_height, model_width, n_classes = model_in model, model_height, model_width, n_classes = model_in
@ -102,10 +102,6 @@ class SbbBinarizer:
img = np.copy(img_padded) img = np.copy(img_padded)
if use_patches:
margin = int(0.1 * model_width) margin = int(0.1 * model_width)
width_mid = model_width - 2 * margin width_mid = model_width - 2 * margin
@ -232,21 +228,9 @@ class SbbBinarizer:
prediction_true = prediction_true[index_start_h: index_start_h+img_org_h, index_start_w: index_start_w+img_org_w,:] prediction_true = prediction_true[index_start_h: index_start_h+img_org_h, index_start_w: index_start_w+img_org_w,:]
prediction_true = prediction_true.astype(np.uint8) prediction_true = prediction_true.astype(np.uint8)
else:
img_h_page = img.shape[0]
img_w_page = img.shape[1]
img = img / float(255.0)
img = resize_image(img, model_height, model_width)
label_p_pred = model.predict(img.reshape(1, img.shape[0], img.shape[1], img.shape[2]))
seg = np.argmax(label_p_pred, axis=3)[0]
seg_color = np.repeat(seg[:, :, np.newaxis], 3, axis=2)
prediction_true = resize_image(seg_color, img_h_page, img_w_page)
prediction_true = prediction_true.astype(np.uint8)
return prediction_true[:,:,0] return prediction_true[:,:,0]
def run(self, image=None, image_path=None, save=None, use_patches=False): def run(self, image=None, image_path=None, save=None):
if (image is not None and image_path is not None) or \ if (image is not None and image_path is not None) or \
(image is None and image_path is None): (image is None and image_path is None):
raise ValueError("Must pass either a opencv2 image or an image_path") raise ValueError("Must pass either a opencv2 image or an image_path")
@ -256,7 +240,7 @@ class SbbBinarizer:
for n, (model, model_file) in enumerate(zip(self.models, self.model_files)): for n, (model, model_file) in enumerate(zip(self.models, self.model_files)):
self.log.info('Predicting with model %s [%s/%s]' % (model_file, n + 1, len(self.model_files))) self.log.info('Predicting with model %s [%s/%s]' % (model_file, n + 1, len(self.model_files)))
res = self.predict(model, image, use_patches) res = self.predict(model, image)
img_fin = np.zeros((res.shape[0], res.shape[1], 3)) img_fin = np.zeros((res.shape[0], res.shape[1], 3))
res[:, :][res[:, :] == 0] = 2 res[:, :][res[:, :] == 0] = 2