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

pull/54/head
vahid 2 years ago
parent eff7a47852
commit 7c3f2176f7

@ -7,9 +7,8 @@ from .sbb_binarize import SbbBinarizer
@command()
@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')
@argument('input_image')
@argument('output_image')
def main(patches, model_dir, input_image, output_image):
SbbBinarizer(model_dir).run(image_path=input_image, use_patches=patches, save=output_image)
def main(model_dir, input_image, output_image):
SbbBinarizer(model_dir).run(image_path=input_image, save=output_image)

@ -110,7 +110,7 @@ class SbbBinarizeProcessor(Processor):
if oplevel == 'page':
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):
bin_image_path = self.workspace.save_image_file(bin_image,
file_id + '.IMG-BIN',
@ -124,7 +124,7 @@ class SbbBinarizeProcessor(Processor):
LOG.warning("Page '%s' contains no text/table regions", page_id)
for region in regions:
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,
"%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)
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_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,
"%s_%s_%s.IMG-BIN" % (file_id, region_id, line.id),

@ -62,7 +62,7 @@ class SbbBinarizer:
n_classes = model.layers[len(model.layers)-1].output_shape[3]
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)
model, model_height, model_width, n_classes = model_in
@ -102,151 +102,135 @@ class SbbBinarizer:
img = np.copy(img_padded)
margin = int(0.1 * model_width)
width_mid = model_width - 2 * margin
height_mid = model_height - 2 * margin
if use_patches:
margin = int(0.1 * model_width)
img = img / float(255.0)
width_mid = model_width - 2 * margin
height_mid = model_height - 2 * margin
img_h = img.shape[0]
img_w = img.shape[1]
prediction_true = np.zeros((img_h, img_w, 3))
mask_true = np.zeros((img_h, img_w))
nxf = img_w / float(width_mid)
nyf = img_h / float(height_mid)
img = img / float(255.0)
img_h = img.shape[0]
img_w = img.shape[1]
prediction_true = np.zeros((img_h, img_w, 3))
mask_true = np.zeros((img_h, img_w))
nxf = img_w / float(width_mid)
nyf = img_h / float(height_mid)
if nxf > int(nxf):
nxf = int(nxf) + 1
else:
nxf = int(nxf)
if nyf > int(nyf):
nyf = int(nyf) + 1
else:
nyf = int(nyf)
for i in range(nxf):
for j in range(nyf):
if nxf > int(nxf):
nxf = int(nxf) + 1
else:
nxf = int(nxf)
if i == 0:
index_x_d = i * width_mid
index_x_u = index_x_d + model_width
elif i > 0:
index_x_d = i * width_mid
index_x_u = index_x_d + model_width
if nyf > int(nyf):
nyf = int(nyf) + 1
else:
nyf = int(nyf)
if j == 0:
index_y_d = j * height_mid
index_y_u = index_y_d + model_height
elif j > 0:
index_y_d = j * height_mid
index_y_u = index_y_d + model_height
for i in range(nxf):
for j in range(nyf):
if index_x_u > img_w:
index_x_u = img_w
index_x_d = img_w - model_width
if index_y_u > img_h:
index_y_u = img_h
index_y_d = img_h - model_height
if i == 0:
index_x_d = i * width_mid
index_x_u = index_x_d + model_width
elif i > 0:
index_x_d = i * width_mid
index_x_u = index_x_d + model_width
img_patch = img[index_y_d:index_y_u, index_x_d:index_x_u, :]
if j == 0:
index_y_d = j * height_mid
index_y_u = index_y_d + model_height
elif j > 0:
index_y_d = j * height_mid
index_y_u = index_y_d + model_height
label_p_pred = model.predict(img_patch.reshape(1, img_patch.shape[0], img_patch.shape[1], img_patch.shape[2]))
if index_x_u > img_w:
index_x_u = img_w
index_x_d = img_w - model_width
if index_y_u > img_h:
index_y_u = img_h
index_y_d = img_h - model_height
seg = np.argmax(label_p_pred, axis=3)[0]
img_patch = img[index_y_d:index_y_u, index_x_d:index_x_u, :]
seg_color = np.repeat(seg[:, :, np.newaxis], 3, axis=2)
label_p_pred = model.predict(img_patch.reshape(1, img_patch.shape[0], img_patch.shape[1], img_patch.shape[2]))
if i == 0 and j == 0:
seg_color = seg_color[0:seg_color.shape[0] - margin, 0:seg_color.shape[1] - margin, :]
seg = seg[0:seg.shape[0] - margin, 0:seg.shape[1] - margin]
seg = np.argmax(label_p_pred, axis=3)[0]
mask_true[index_y_d + 0:index_y_u - margin, index_x_d + 0:index_x_u - margin] = seg
prediction_true[index_y_d + 0:index_y_u - margin, index_x_d + 0:index_x_u - margin, :] = seg_color
seg_color = np.repeat(seg[:, :, np.newaxis], 3, axis=2)
elif i == nxf-1 and j == nyf-1:
seg_color = seg_color[margin:seg_color.shape[0] - 0, margin:seg_color.shape[1] - 0, :]
seg = seg[margin:seg.shape[0] - 0, margin:seg.shape[1] - 0]
if i == 0 and j == 0:
seg_color = seg_color[0:seg_color.shape[0] - margin, 0:seg_color.shape[1] - margin, :]
seg = seg[0:seg.shape[0] - margin, 0:seg.shape[1] - margin]
mask_true[index_y_d + margin:index_y_u - 0, index_x_d + margin:index_x_u - 0] = seg
prediction_true[index_y_d + margin:index_y_u - 0, index_x_d + margin:index_x_u - 0, :] = seg_color
mask_true[index_y_d + 0:index_y_u - margin, index_x_d + 0:index_x_u - margin] = seg
prediction_true[index_y_d + 0:index_y_u - margin, index_x_d + 0:index_x_u - margin, :] = seg_color
elif i == 0 and j == nyf-1:
seg_color = seg_color[margin:seg_color.shape[0] - 0, 0:seg_color.shape[1] - margin, :]
seg = seg[margin:seg.shape[0] - 0, 0:seg.shape[1] - margin]
elif i == nxf-1 and j == nyf-1:
seg_color = seg_color[margin:seg_color.shape[0] - 0, margin:seg_color.shape[1] - 0, :]
seg = seg[margin:seg.shape[0] - 0, margin:seg.shape[1] - 0]
mask_true[index_y_d + margin:index_y_u - 0, index_x_d + 0:index_x_u - margin] = seg
prediction_true[index_y_d + margin:index_y_u - 0, index_x_d + 0:index_x_u - margin, :] = seg_color
mask_true[index_y_d + margin:index_y_u - 0, index_x_d + margin:index_x_u - 0] = seg
prediction_true[index_y_d + margin:index_y_u - 0, index_x_d + margin:index_x_u - 0, :] = seg_color
elif i == nxf-1 and j == 0:
seg_color = seg_color[0:seg_color.shape[0] - margin, margin:seg_color.shape[1] - 0, :]
seg = seg[0:seg.shape[0] - margin, margin:seg.shape[1] - 0]
elif i == 0 and j == nyf-1:
seg_color = seg_color[margin:seg_color.shape[0] - 0, 0:seg_color.shape[1] - margin, :]
seg = seg[margin:seg.shape[0] - 0, 0:seg.shape[1] - margin]
mask_true[index_y_d + 0:index_y_u - margin, index_x_d + margin:index_x_u - 0] = seg
prediction_true[index_y_d + 0:index_y_u - margin, index_x_d + margin:index_x_u - 0, :] = seg_color
mask_true[index_y_d + margin:index_y_u - 0, index_x_d + 0:index_x_u - margin] = seg
prediction_true[index_y_d + margin:index_y_u - 0, index_x_d + 0:index_x_u - margin, :] = seg_color
elif i == 0 and j != 0 and j != nyf-1:
seg_color = seg_color[margin:seg_color.shape[0] - margin, 0:seg_color.shape[1] - margin, :]
seg = seg[margin:seg.shape[0] - margin, 0:seg.shape[1] - margin]
elif i == nxf-1 and j == 0:
seg_color = seg_color[0:seg_color.shape[0] - margin, margin:seg_color.shape[1] - 0, :]
seg = seg[0:seg.shape[0] - margin, margin:seg.shape[1] - 0]
mask_true[index_y_d + margin:index_y_u - margin, index_x_d + 0:index_x_u - margin] = seg
prediction_true[index_y_d + margin:index_y_u - margin, index_x_d + 0:index_x_u - margin, :] = seg_color
mask_true[index_y_d + 0:index_y_u - margin, index_x_d + margin:index_x_u - 0] = seg
prediction_true[index_y_d + 0:index_y_u - margin, index_x_d + margin:index_x_u - 0, :] = seg_color
elif i == nxf-1 and j != 0 and j != nyf-1:
seg_color = seg_color[margin:seg_color.shape[0] - margin, margin:seg_color.shape[1] - 0, :]
seg = seg[margin:seg.shape[0] - margin, margin:seg.shape[1] - 0]
elif i == 0 and j != 0 and j != nyf-1:
seg_color = seg_color[margin:seg_color.shape[0] - margin, 0:seg_color.shape[1] - margin, :]
seg = seg[margin:seg.shape[0] - margin, 0:seg.shape[1] - margin]
mask_true[index_y_d + margin:index_y_u - margin, index_x_d + margin:index_x_u - 0] = seg
prediction_true[index_y_d + margin:index_y_u - margin, index_x_d + margin:index_x_u - 0, :] = seg_color
mask_true[index_y_d + margin:index_y_u - margin, index_x_d + 0:index_x_u - margin] = seg
prediction_true[index_y_d + margin:index_y_u - margin, index_x_d + 0:index_x_u - margin, :] = seg_color
elif i != 0 and i != nxf-1 and j == 0:
seg_color = seg_color[0:seg_color.shape[0] - margin, margin:seg_color.shape[1] - margin, :]
seg = seg[0:seg.shape[0] - margin, margin:seg.shape[1] - margin]
elif i == nxf-1 and j != 0 and j != nyf-1:
seg_color = seg_color[margin:seg_color.shape[0] - margin, margin:seg_color.shape[1] - 0, :]
seg = seg[margin:seg.shape[0] - margin, margin:seg.shape[1] - 0]
mask_true[index_y_d + 0:index_y_u - margin, index_x_d + margin:index_x_u - margin] = seg
prediction_true[index_y_d + 0:index_y_u - margin, index_x_d + margin:index_x_u - margin, :] = seg_color
mask_true[index_y_d + margin:index_y_u - margin, index_x_d + margin:index_x_u - 0] = seg
prediction_true[index_y_d + margin:index_y_u - margin, index_x_d + margin:index_x_u - 0, :] = seg_color
elif i != 0 and i != nxf-1 and j == nyf-1:
seg_color = seg_color[margin:seg_color.shape[0] - 0, margin:seg_color.shape[1] - margin, :]
seg = seg[margin:seg.shape[0] - 0, margin:seg.shape[1] - margin]
elif i != 0 and i != nxf-1 and j == 0:
seg_color = seg_color[0:seg_color.shape[0] - margin, margin:seg_color.shape[1] - margin, :]
seg = seg[0:seg.shape[0] - margin, margin:seg.shape[1] - margin]
mask_true[index_y_d + margin:index_y_u - 0, index_x_d + margin:index_x_u - margin] = seg
prediction_true[index_y_d + margin:index_y_u - 0, index_x_d + margin:index_x_u - margin, :] = seg_color
mask_true[index_y_d + 0:index_y_u - margin, index_x_d + margin:index_x_u - margin] = seg
prediction_true[index_y_d + 0:index_y_u - margin, index_x_d + margin:index_x_u - margin, :] = seg_color
else:
seg_color = seg_color[margin:seg_color.shape[0] - margin, margin:seg_color.shape[1] - margin, :]
seg = seg[margin:seg.shape[0] - margin, margin:seg.shape[1] - margin]
elif i != 0 and i != nxf-1 and j == nyf-1:
seg_color = seg_color[margin:seg_color.shape[0] - 0, margin:seg_color.shape[1] - margin, :]
seg = seg[margin:seg.shape[0] - 0, margin:seg.shape[1] - margin]
mask_true[index_y_d + margin:index_y_u - margin, index_x_d + margin:index_x_u - margin] = seg
prediction_true[index_y_d + margin:index_y_u - margin, index_x_d + margin:index_x_u - margin, :] = seg_color
mask_true[index_y_d + margin:index_y_u - 0, index_x_d + margin:index_x_u - margin] = seg
prediction_true[index_y_d + margin:index_y_u - 0, index_x_d + margin:index_x_u - margin, :] = seg_color
else:
seg_color = seg_color[margin:seg_color.shape[0] - margin, margin:seg_color.shape[1] - margin, :]
seg = seg[margin:seg.shape[0] - margin, margin:seg.shape[1] - margin]
mask_true[index_y_d + margin:index_y_u - margin, index_x_d + margin:index_x_u - margin] = seg
prediction_true[index_y_d + margin:index_y_u - margin, index_x_d + margin:index_x_u - margin, :] = seg_color
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)
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]))
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)
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]
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 \
(image is None and image_path is None):
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)):
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))
res[:, :][res[:, :] == 0] = 2

Loading…
Cancel
Save