def line_extraction_v1(
probs: np.ndarray,
low_threshold: float,
high_threshold: float,
sigma: float = 0.0,
filter_width: float = 0.00,
vertical_maxima: bool = False) -> Tuple[List[np.ndarray], np.ndarray]:
# Smooth
probs2 = cleaning_probs(probs, sigma=sigma)
lines_mask = hysteresis_thresholding(
probs2,
low_threshold,
high_threshold,
candidates_mask=vertical_local_maxima(probs2)
if vertical_maxima else None)
# Remove lines touching border
# lines_mask = remove_borders(lines_mask)
# Extract polygons from line mask
contours = find_lines(lines_mask)
filtered_contours = []
page_width = probs.shape[1]
for cnt in contours:
centroid_x, centroid_y = np.mean(cnt, axis=0)[0]
if centroid_x < filter_width * page_width or centroid_x > (
1 - filter_width) * page_width:
continue
# if cv2.arcLength(cnt, False) < filter_width*page_width:
# continue
filtered_contours.append(cnt)
return filtered_contours, lines_mask
def line_extraction_v1(
probs: np.ndarray,
low_threshold: float,
high_threshold: float,
sigma: float = 0.0,
filter_width: float = 0.00,
vertical_maxima: bool = False) -> Tuple[List[np.ndarray], np.ndarray]:
"""
Given a probability map, returns the contour of lines and the corresponding mask
:param probs: probability map (numpy array)
:param low_threshold: hysteresis low threshold
:param high_threshold: hysteresis high threshold
:param sigma: sigma value for gaussian filtering
:param filter_width: percentage of the image width to filter out lines that are close to borders (default 0.0)
:param vertical_maxima: set to True to use vertical local maxima as candidates for the hysteresis thresholding
:return:
"""
# Smooth
probs2 = cleaning_probs(probs, sigma=sigma)
lines_mask = hysteresis_thresholding(
probs2,
low_threshold,
high_threshold,
candidates_mask=vertical_local_maxima(probs2)
if vertical_maxima else None)
# Remove lines touching border
# lines_mask = remove_borders(lines_mask)
# Extract polygons from line mask
contours = find_lines(lines_mask)
filtered_contours = []
page_width = probs.shape[1]
for cnt in contours:
centroid_x, centroid_y = np.mean(cnt, axis=0)[0]
if centroid_x < filter_width * page_width or centroid_x > (
1 - filter_width) * page_width:
continue
# if cv2.arcLength(cnt, False) < filter_width*page_width:
# continue
filtered_contours.append(cnt)
return filtered_contours, lines_mask