1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
| import os
import math
import numpy as np
from PIL import Image
from skimage.morphology import binary_dilation, disk
def db_eval_iou(annotation, segmentation):
"""
Compute region similarity as the Jaccard Index.
Arguments:
annotation (ndarray): binary annotation map.
segmentation (ndarray): binary segmentation map.
Return:
jaccard (float): region similarity
"""
annotation = annotation.astype(np.bool_)
segmentation = segmentation.astype(np.bool_)
if np.isclose(np.sum(annotation), 0) and np.isclose(np.sum(segmentation), 0):
return 1
else:
return np.sum((annotation & segmentation)) / np.sum((annotation | segmentation), dtype=np.float32)
def db_eval_boundary(foreground_mask, gt_mask, bound_th=0.008):
"""
Compute mean, recall and decay from per-frame evaluation.
Calculates precision/recall for boundaries between foreground_mask and
gt_mask using morphological operators to speed it up.
Arguments:
foreground_mask (ndarray): binary segmentation image.
gt_mask (ndarray): binary annotated image.
Returns:
F (float): boundaries F-measure
P (float): boundaries precision
R (float): boundaries recall
"""
assert np.atleast_3d(foreground_mask).shape[2] == 1
bound_pix = bound_th if bound_th >= 1 else \
np.ceil(bound_th * np.linalg.norm(foreground_mask.shape))
fg_boundary = seg2bmap(foreground_mask)
gt_boundary = seg2bmap(gt_mask)
fg_dil = binary_dilation(fg_boundary, disk(bound_pix))
gt_dil = binary_dilation(gt_boundary, disk(bound_pix))
gt_match = gt_boundary * fg_dil
fg_match = fg_boundary * gt_dil
n_fg = np.sum(fg_boundary)
n_gt = np.sum(gt_boundary)
if n_fg == 0 and n_gt > 0:
precision = 1
recall = 0
elif n_fg > 0 and n_gt == 0:
precision = 0
recall = 1
elif n_fg == 0 and n_gt == 0:
precision = 1
recall = 1
else:
precision = np.sum(fg_match) / float(n_fg)
recall = np.sum(gt_match) / float(n_gt)
if precision + recall == 0:
F_score = 0
else:
F_score = 2 * precision * recall / (precision + recall)
return F_score
def seg2bmap(seg, width=None, height=None):
"""
From a segmentation, compute a binary boundary map with 1 pixel wide
boundaries. The boundary pixels are offset by 1/2 pixel towards the
origin from the actual segment boundary.
Arguments:
seg : Segments labeled from 1..k.
width : Width of desired bmap <= seg.shape[1]
height : Height of desired bmap <= seg.shape[0]
Returns:
bmap (ndarray): Binary boundary map.
"""
seg = seg.astype(np.bool_)
seg[seg > 0] = 1
assert np.atleast_3d(seg).shape[2] == 1
width = seg.shape[1] if width is None else width
height = seg.shape[0] if height is None else height
h,w = seg.shape[:2]
ar1 = float(width) / float(height)
ar2 = float(w) / float(h)
assert not (width > w | height > h | abs(ar1 - ar2) > 0.01),\
'Can''t convert %dx%d seg to %dx%d bmap.'%(w, h, width, height)
e = np.zeros_like(seg)
s = np.zeros_like(seg)
se = np.zeros_like(seg)
e[:, :-1] = seg[:, 1:]
s[:-1, :] = seg[1:, :]
se[:-1, :-1] = seg[1:, 1:]
b = seg^e | seg^s | seg^se
b[-1, :] = seg[-1, :]^e[-1, :]
b[:, -1] = seg[:, -1]^s[:, -1]
b[-1, -1] = 0
if w == width and h == height:
bmap = b
else:
bmap = np.zeros((height, width))
for x in range(w):
for y in range(h):
if b[y, x]:
j = 1 + math.floor((y - 1) + height / h)
i = 1 + math.floor((x - 1) + width / h)
bmap[j, i] = 1
return bmap
database_path = '../data/mask_database/'
test_path = '../data/mask_test/'
database_img_name_list = os.listdir(database_path)
test_img_name_list = os.listdir(test_path)
for test_img_name in test_img_name_list:
test_img = Image.open(test_path + test_img_name)
h, w = test_img.size
test_img = np.asarray(test_img)
best_iou, best_F, best_iou_dbname, best_F_dbname = 0.0, 0.0, None, None
for database_img_name in database_img_name_list:
database_img = Image.open(database_path + database_img_name).resize((h, w))
database_img = np.asarray(database_img)
iou = db_eval_iou(test_img, database_img)
F_score = db_eval_boundary(test_img, database_img)
if iou > best_iou:
best_iou = iou
best_iou_dbname = database_img_name
if F_score > best_F:
best_F = F_score
best_F_dbname = database_img_name
print(f'[{test_img_name}] best iou: {best_iou:.4f} ({best_iou_dbname}), best F: {best_F:.4f} ({best_F_dbname})')
|