def segment(im, scale=None, black_colseps=False):
"""
Segments a page into text lines.
Segments a page into text lines and returns the absolute coordinates of
each line in reading order.
Args:
im (PIL.Image): A bi-level page of mode '1' or 'L'
scale (float): Scale of the image
black_colseps (bool): Whether column separators are assumed to be
vertical black lines or not
Returns:
[(x1, y1, x2, y2),...]: A list of tuples containing the bounding boxes
of the segmented lines in reading order.
Raises:
KrakenInputException if the input image is not binarized
"""
if im.mode != '1' and not is_bitonal(im):
raise KrakenInputException('Image is not bi-level')
# honestly I've got no idea what's going on here. In theory a simple
# np.array(im, 'i') should suffice here but for some reason the
# tostring/fromstring magic in pil2array alters the array in a way that is
# needed for the algorithm to work correctly.
a = pil2array(im)
binary = np.array(a > 0.5 * (np.amin(a) + np.amax(a)), 'i')
binary = 1 - binary
if not scale:
scale = estimate_scale(binary)
binary = remove_hlines(binary, scale)
if black_colseps:
colseps, binary = compute_black_colseps(binary, scale)
else:
colseps = compute_white_colseps(binary, scale)
bottom, top, boxmap = compute_gradmaps(binary, scale)
seeds = compute_line_seeds(binary, bottom, top, colseps, scale)
llabels = morph.propagate_labels(boxmap, seeds, conflict=0)
spread = morph.spread_labels(seeds, maxdist=scale)
llabels = np.where(llabels > 0, llabels, spread * binary)
segmentation = llabels * binary
lines = compute_lines(segmentation, scale)
order = reading_order([l.bounds for l in lines])
lsort = topsort(order)
lines = [lines[i].bounds for i in lsort]
return [(s2.start, s1.start, s2.stop, s1.stop) for s1, s2 in lines]
def segment(im, scale=None, black_colseps=False):
"""
Segments a page into text lines.
Segments a page into text lines and returns the absolute coordinates of
each line in reading order.
Args:
im (PIL.Image): A bi-level page of mode '1' or 'L'
scale (float): Scale of the image
black_colseps (bool): Whether column separators are assumed to be
vertical black lines or not
Returns:
[(x1, y1, x2, y2),...]: A list of tuples containing the bounding boxes
of the segmented lines in reading order.
Raises:
KrakenInputException if the input image is not binarized
"""
if im.mode != '1' and im.histogram().count(0) != 254:
raise KrakenInputException('Image is not bi-level')
# honestly I've got no idea what's going on here. In theory a simple
# np.array(im, 'i') should suffice here but for some reason the
# tostring/fromstring magic in pil2array alters the array in a way that is
# needed for the algorithm to work correctly.
a = pil2array(im)
binary = np.array(a > 0.5*(np.amin(a) + np.amax(a)), 'i')
binary = 1 - binary
if not scale:
scale = estimate_scale(binary)
binary = remove_hlines(binary, scale)
if black_colseps:
colseps, binary = compute_black_colseps(binary, scale)
else:
colseps = compute_white_colseps(binary, scale)
bottom, top, boxmap = compute_gradmaps(binary, scale)
seeds = compute_line_seeds(binary, bottom, top, colseps, scale)
llabels = morph.propagate_labels(boxmap, seeds, conflict=0)
spread = morph.spread_labels(seeds, maxdist=scale)
llabels = np.where(llabels > 0, llabels, spread*binary)
segmentation = llabels*binary
lines = compute_lines(segmentation, scale)
order = reading_order([l.bounds for l in lines])
lsort = topsort(order)
lines = [lines[i].bounds for i in lsort]
return [(s2.start, s1.start, s2.stop, s1.stop) for s1, s2 in lines]
def segment(im,
text_direction: str = 'horizontal-lr',
scale: Optional[float] = None,
maxcolseps: float = 2,
black_colseps: bool = False,
no_hlines: bool = True,
pad: int = 0,
mask: Optional[np.array] = None,
reading_order_fn: Callable = reading_order) -> Dict[str, Any]:
"""
Segments a page into text lines.
Segments a page into text lines and returns the absolute coordinates of
each line in reading order.
Args:
im (PIL.Image): A bi-level page of mode '1' or 'L'
text_direction (str): Principal direction of the text
(horizontal-lr/rl/vertical-lr/rl)
scale (float): Scale of the image
maxcolseps (int): Maximum number of whitespace column separators
black_colseps (bool): Whether column separators are assumed to be
vertical black lines or not
no_hlines (bool): Switch for horizontal line removal
pad (int or tuple): Padding to add to line bounding boxes. If int the
same padding is used both left and right. If a
2-tuple, uses (padding_left, padding_right).
mask (PIL.Image): A bi-level mask image of the same size as `im` where
0-valued regions are ignored for segmentation
purposes. Disables column detection.
reading_order_fn (Callable): Function to call to order line output.
Callable accepting a list of slices (y, x)
and a text direction in (`rl`, `lr`).
Returns:
{'text_direction': '$dir', 'boxes': [(x1, y1, x2, y2),...]}: A
dictionary containing the text direction and a list of reading order
sorted bounding boxes under the key 'boxes'.
Raises:
KrakenInputException if the input image is not binarized or the text
direction is invalid.
"""
im_str = get_im_str(im)
logger.info(f'Segmenting {im_str}')
if im.mode != '1' and not is_bitonal(im):
logger.error(f'Image {im_str} is not bi-level')
raise KrakenInputException(f'Image {im_str} is not bi-level')
# rotate input image for vertical lines
if text_direction.startswith('horizontal'):
angle = 0
offset = (0, 0)
elif text_direction == 'vertical-lr':
angle = 270
offset = (0, im.size[1])
elif text_direction == 'vertical-rl':
angle = 90
offset = (im.size[0], 0)
else:
logger.error(f'Invalid text direction \'{text_direction}\'')
raise KrakenInputException(f'Invalid text direction {text_direction}')
logger.debug(f'Rotating input image by {angle} degrees')
im = im.rotate(angle, expand=True)
a = pil2array(im)
binary = np.array(a > 0.5 * (np.amin(a) + np.amax(a)), 'i')
binary = 1 - binary
if not scale:
scale = estimate_scale(binary)
if no_hlines:
binary = remove_hlines(binary, scale)
# emptyish images wll cause exceptions here.
try:
if mask:
if mask.mode != '1' and not is_bitonal(mask):
logger.error('Mask is not bitonal')
raise KrakenInputException('Mask is not bitonal')
mask = mask.convert('1')
if mask.size != im.size:
logger.error(
f'Mask size {mask.size} doesn\'t match image size {im.size}'
)
raise KrakenInputException(
f'Mask size {mask.size} doesn\'t match image size {im.size}'
)
logger.info(
'Masking enabled in segmenter. Disabling column detection.')
mask = mask.rotate(angle, expand=True)
colseps = pil2array(mask)
elif black_colseps:
colseps, binary = compute_black_colseps(binary, scale, maxcolseps)
else:
colseps = compute_white_colseps(binary, scale, maxcolseps)
except ValueError:
logger.warning(
f'Exception in column finder (probably empty image) for {im_str}')
return {'text_direction': text_direction, 'boxes': []}
bottom, top, boxmap = compute_gradmaps(binary, scale)
seeds = compute_line_seeds(binary, bottom, top, colseps, scale)
llabels = morph.propagate_labels(boxmap, seeds, conflict=0)
spread = morph.spread_labels(seeds, maxdist=scale)
llabels = np.where(llabels > 0, llabels, spread * binary)
segmentation = llabels * binary
lines = compute_lines(segmentation, scale)
order = reading_order_fn([l.bounds for l in lines], text_direction[-2:])
lsort = topsort(order)
lines = [lines[i].bounds for i in lsort]
lines = [(s2.start, s1.start, s2.stop, s1.stop) for s1, s2 in lines]
if isinstance(pad, int):
pad = (pad, pad)
lines = [(max(x[0] - pad[0], 0), x[1], min(x[2] + pad[1],
im.size[0]), x[3])
for x in lines]
return {
'text_direction': text_direction,
'boxes': rotate_lines(lines, 360 - angle, offset).tolist(),
'script_detection': False
}
def segment(im,
text_direction='horizontal-lr',
scale=None,
maxcolseps=2,
black_colseps=False):
"""
Segments a page into text lines.
Segments a page into text lines and returns the absolute coordinates of
each line in reading order.
Args:
im (PIL.Image): A bi-level page of mode '1' or 'L'
text_direction (str): Principal direction of the text
(horizontal-lr/rl/vertical-lr/rl)
scale (float): Scale of the image
maxcolseps (int): Maximum number of whitespace column separators
black_colseps (bool): Whether column separators are assumed to be
vertical black lines or not
Returns:
{'text_direction': '$dir', 'boxes': [(x1, y1, x2, y2),...]}: A
dictionary containing the text direction and a list of reading order
sorted bounding boxes under the key 'boxes'.
Raises:
KrakenInputException if the input image is not binarized or the text
direction is invalid.
"""
if im.mode != '1' and not is_bitonal(im):
raise KrakenInputException('Image is not bi-level')
# rotate input image for vertical lines
if text_direction.startswith('horizontal'):
angle = 0
offset = (0, 0)
elif text_direction == 'vertical-lr':
angle = 270
offset = (0, im.size[1])
elif text_direction == 'vertical-rl':
angle = 90
offset = (im.size[0], 0)
else:
raise KrakenInputException('Invalid text direction')
im = im.rotate(angle, expand=True)
# honestly I've got no idea what's going on here. In theory a simple
# np.array(im, 'i') should suffice here but for some reason the
# tostring/fromstring magic in pil2array alters the array in a way that is
# needed for the algorithm to work correctly.
a = pil2array(im)
binary = np.array(a > 0.5 * (np.amin(a) + np.amax(a)), 'i')
binary = 1 - binary
if not scale:
scale = estimate_scale(binary)
binary = remove_hlines(binary, scale)
# emptyish images wll cause exceptions here.
try:
if black_colseps:
colseps, binary = compute_black_colseps(binary, scale, maxcolseps)
else:
colseps = compute_white_colseps(binary, scale, maxcolseps)
except ValueError:
return {'text_direction': text_direction, 'boxes': []}
bottom, top, boxmap = compute_gradmaps(binary, scale)
seeds = compute_line_seeds(binary, bottom, top, colseps, scale)
llabels = morph.propagate_labels(boxmap, seeds, conflict=0)
spread = morph.spread_labels(seeds, maxdist=scale)
llabels = np.where(llabels > 0, llabels, spread * binary)
segmentation = llabels * binary
lines = compute_lines(segmentation, scale)
order = reading_order([l.bounds for l in lines], text_direction[-2:])
lsort = topsort(order)
lines = [lines[i].bounds for i in lsort]
lines = [(s2.start, s1.start, s2.stop, s1.stop) for s1, s2 in lines]
return {
'text_direction': text_direction,
'boxes': rotate_lines(lines, 360 - angle, offset).tolist(),
'script_detection': False
}
def segment(im, text_direction='horizontal-lr', scale=None, maxcolseps=2,
black_colseps=False, no_hlines=True, pad=0, mask=None):
"""
Segments a page into text lines.
Segments a page into text lines and returns the absolute coordinates of
each line in reading order.
Args:
im (PIL.Image): A bi-level page of mode '1' or 'L'
text_direction (str): Principal direction of the text
(horizontal-lr/rl/vertical-lr/rl)
scale (float): Scale of the image
maxcolseps (int): Maximum number of whitespace column separators
black_colseps (bool): Whether column separators are assumed to be
vertical black lines or not
no_hlines (bool): Switch for horizontal line removal
pad (int or tuple): Padding to add to line bounding boxes. If int the
same padding is used both left and right. If a
2-tuple, uses (padding_left, padding_right).
mask (PIL.Image): A bi-level mask image of the same size as `im` where
0-valued regions are ignored for segmentation
purposes. Disables column detection.
Returns:
{'text_direction': '$dir', 'boxes': [(x1, y1, x2, y2),...]}: A
dictionary containing the text direction and a list of reading order
sorted bounding boxes under the key 'boxes'.
Raises:
KrakenInputException if the input image is not binarized or the text
direction is invalid.
"""
im_str = get_im_str(im)
logger.info('Segmenting {}'.format(im_str))
if im.mode != '1' and not is_bitonal(im):
logger.error('Image {} is not bi-level'.format(im_str))
raise KrakenInputException('Image {} is not bi-level'.format(im_str))
# rotate input image for vertical lines
if text_direction.startswith('horizontal'):
angle = 0
offset = (0, 0)
elif text_direction == 'vertical-lr':
angle = 270
offset = (0, im.size[1])
elif text_direction == 'vertical-rl':
angle = 90
offset = (im.size[0], 0)
else:
logger.error('Invalid text direction \'{}\''.format(text_direction))
raise KrakenInputException('Invalid text direction {}'.format(text_direction))
logger.debug('Rotating input image by {} degrees'.format(angle))
im = im.rotate(angle, expand=True)
# honestly I've got no idea what's going on here. In theory a simple
# np.array(im, 'i') should suffice here but for some reason the
# tostring/fromstring magic in pil2array alters the array in a way that is
# needed for the algorithm to work correctly.
a = pil2array(im)
binary = np.array(a > 0.5*(np.amin(a) + np.amax(a)), 'i')
binary = 1 - binary
if not scale:
scale = estimate_scale(binary)
if no_hlines:
binary = remove_hlines(binary, scale)
# emptyish images wll cause exceptions here.
try:
if mask:
if mask.mode != '1' and not is_bitonal(mask):
logger.error('Mask is not bitonal')
raise KrakenInputException('Mask is not bitonal')
mask = mask.convert('1')
if mask.size != im.size:
logger.error('Mask size {} doesn\'t match image size {}'.format(mask.size, im.size))
raise KrakenInputException('Mask size {} doesn\'t match image size {}'.format(mask.size, im.size))
logger.info('Masking enabled in segmenter. Disabling column detection.')
mask = mask.rotate(angle, expand=True)
colseps = pil2array(mask)
elif black_colseps:
colseps, binary = compute_black_colseps(binary, scale, maxcolseps)
else:
colseps = compute_white_colseps(binary, scale, maxcolseps)
except ValueError:
logger.warning('Exception in column finder (probably empty image) for {}.'.format(im_str))
return {'text_direction': text_direction, 'boxes': []}
bottom, top, boxmap = compute_gradmaps(binary, scale)
seeds = compute_line_seeds(binary, bottom, top, colseps, scale)
llabels = morph.propagate_labels(boxmap, seeds, conflict=0)
spread = morph.spread_labels(seeds, maxdist=scale)
llabels = np.where(llabels > 0, llabels, spread*binary)
segmentation = llabels*binary
lines = compute_lines(segmentation, scale)
order = reading_order([l.bounds for l in lines], text_direction[-2:])
lsort = topsort(order)
lines = [lines[i].bounds for i in lsort]
lines = [(s2.start, s1.start, s2.stop, s1.stop) for s1, s2 in lines]
if isinstance(pad, int):
pad = (pad, pad)
lines = [(max(x[0]-pad[0], 0), x[1], min(x[2]+pad[1], im.size[0]), x[3]) for x in lines]
return {'text_direction': text_direction, 'boxes': rotate_lines(lines, 360-angle, offset).tolist(), 'script_detection': False}