def remove_hlines(binary, scale, maxsize=10):
"""
Removes horizontal black lines that only interfere with page segmentation.
Args:
binary (numpy.array):
scale (float):
maxsize (int): maximum size of removed lines
Returns:
numpy.array containing the filtered image.
"""
labels, _ = morph.label(binary)
objects = morph.find_objects(labels)
for i, b in enumerate(objects):
if sl.width(b) > maxsize*scale:
labels[b][labels[b] == i+1] = 0
return np.array(labels != 0, 'B')
def remove_hlines(binary, scale, maxsize=10):
"""
Removes horizontal black lines that only interfere with page segmentation.
Args:
binary (numpy.array):
scale (float):
maxsize (int): maximum size of removed lines
Returns:
numpy.array containing the filtered image.
"""
labels, _ = morph.label(binary)
objects = morph.find_objects(labels)
for i, b in enumerate(objects):
if sl.width(b) > maxsize * scale:
labels[b][labels[b] == i + 1] = 0
return np.array(labels != 0, 'B')
def remove_hlines(binary: np.ndarray,
scale: float,
maxsize: int = 10) -> np.ndarray:
"""
Removes horizontal black lines that only interfere with page segmentation.
Args:
binary:
scale:
maxsize: maximum size of removed lines
Returns:
numpy.ndarray containing the filtered image.
"""
logger.debug('Filtering horizontal lines')
labels, _ = morph.label(binary)
objects = morph.find_objects(labels)
for i, b in enumerate(objects):
if sl.width(b) > maxsize * scale:
labels[b][labels[b] == i + 1] = 0
return np.array(labels != 0, 'B')