def _extract_image_and_mask_from_path(img_path, mask_path, textboxes, multiple):
img = path2img(img_path)
if mask_path is None:
text_mask = 1 - generate_text_mask(img.shape[:2], textboxes) # returns all 1's if textboxes == None
return [(img, text_mask), ]
mask = path2mask(mask_path)
text_mask = 1 - generate_text_mask(mask.shape, textboxes)
if multiple:
masks = extract_paintings_from_mask(mask)
if masks is None or len(masks) == 0:
return [(img, np.ones(img.shape[:2]).astype(np.uint8)), ]
return [(img, ((text_mask != 0) & (m != 0)).astype(np.uint8)) for m in masks]
return [(img, ((text_mask != 0) & (mask != 0)).astype(np.uint8)), ]
def _extract_features_from_path_mask(_path, _path_mask, textboxes):
img, mask = path2img(_path), path2mask(_path_mask)
text_mask = 1 - generate_text_mask(mask.shape, textboxes)
if multiple:
masks = extract_paintings_from_mask(mask)
#print(f"{_path_mask} - {len(masks)}")
return [
extract_features_func(img,
mask=((text_mask != 0) &
(m != 0)).astype(np.uint8))
for m in masks
]
return [
extract_features_func(img,
mask=((text_mask != 0) & (mask != 0)).astype(
np.uint8)),
]
def extract_textbox(orig_img, mask=None):
"""
Given an image (and a mask), extracts the textbox in it, if any found (taking into account a metric).
Parameters
----------
orig_img : image from which extract the textbox
mask : mask to use. In case of multiple paintings, each connected component will be considered as a different
painting.
Returns
-------
score: bboxes (0 or 1 per connected component found in the mask)
"""
masks = []
shapes = []
bboxes = []
# extract each painting's mask
if mask is None:
masks = [np.ones(orig_img.shape[:2])]
else:
masks = extract_paintings_from_mask(mask)
if masks is None:
return [[0, 0, 0, 0]]
# we try to extract one textbox per painting
for m in masks:
img = orig_img.copy()
img[m == 0] = (0, 0, 0)
sc_br, bbox_br = get_best_textbox_candidate(brightText(img), m)
sc_dr, bbox_dr = get_best_textbox_candidate(darkText(img), m)
bbox = bbox_br
if sc_dr == 0 and sc_br == 0:
continue
if sc_dr > sc_br:
bbox = bbox_dr
bboxes.append(bbox)
return bboxes
def apply_filters(mask, filters, img=None):
mask_copy = mask.copy()
metadata_list = []
# apply consecutive filters to a mask.
for i in range(len(filters)):
f = filters[i]
final_mask = np.zeros_like(mask)
masks = extract_paintings_from_mask(mask)
#num_labels, labels = cv2.connectedComponents(mask.astype(np.uint8))
#for lab in range(1, num_labels):
#m = (labels == lab).astype(np.uint8)
# we will always have a painting
if masks is None or len(masks) == 0:
x, y, w, h = cv2.boundingRect(mask_copy)
mask_copy[y:y+h, x:x+w] = 255
return mask_copy, (extract_angle(img) if img is not None else 0.0, [[x, y], [x+w, y], [x+w, y+h], [x, y+h]])
for m in masks:
_,_, w, h = cv2.boundingRect(m)
if w / mask.shape[1] < 0.15 or h / mask.shape[1] < 0.15:
continue
f_m, metadata = f(m, img=img)
final_mask += f_m.astype(np.uint8)
# last filter gives us the metadata: [angle, [p1,p2,p3,p4]]
if i == len(filters) - 1:
metadata_list.append(metadata)
mask = final_mask
"""
# we will always have a painting
x, y, w, h = cv2.boundingRect(final_mask)
if w / mask.shape[1] < 0.10 or h / mask.shape[1] < 0.10:
x, y, w, h = cv2.boundingRect(mask_copy)
mask_copy[y:y+h, x:x+w] = 255
return mask_copy, (extract_angle(img) if img is not None else 0.0, [[x, y], [x+w, y], [x+w, y+h], [x, y+h]])
"""
return final_mask, metadata_list
