Information Technology Reference
In-Depth Information
Table 3 Comparative WBC detection among methods that considers the complete data set of 30
images corrupted by different levels of Salt and Pepper noise
Noise level
Method
Leukocytes
detected
Missing
False
alarms
DR
(%)
FAR
(%)
5 % Salt and Pepper
noise 517 leukocytes
BSV [3]
185
332
133
34.74
26.76
IO [4]
311
206
106
63.38
24.88
Wang [5]
250
176
121
58.68
27.70
GAB [16]
298
219
135
71.83
24.18
DE-based
482
35
32
91.55
7.04
10 % Salt and Pepper
noise 517 leukocytes
BSV [3]
105
412
157
20.31
30.37
IO [4]
276
241
110
53.38
21.28
Wang [5]
214
303
168
41.39
32.49
GAB [16]
337
180
98
65.18
18.95
DE-based
463
54
31
89.55
5.99
Table 4 Comparative WBC detection among methods that considers the complete data set of 30
images corrupted by different levels of Gaussian noise
Noise level
Method
Leukocytes
detected
Missing
False
alarms
DR
(%)
FAR
(%)
r ¼
5 Gaussian noise
517 leukocytes
BSV [3]
214
303
98
41.39
18.95
IO [4]
366
151
87
70.79
16.83
Wang [5]
358
159
84
69.25
16.25
GAB [16]
407
110
76
78.72
14.70
DE-based
487
30
21
94.20
4.06
r ¼ 10 Gaussian
noise 517 leukocytes
BSV [3]
162
355
129
31.33
24.95
IO [4]
331
186
112
64.02
21.66
Wang [5]
315
202
124
60.93
23.98
GAB [16]
363
154
113
70.21
21.86
DE-based
471
46
35
91.10
6.77
The Wang algorithm is an energy-minimizing method which is guided by
internal constraint elements and in
fl
uenced by external image forces, producing the
segmentation of WBC
s at a closed contour. As external forces, the Wang approach
uses edge information which is usually represented by the gradient magnitude of the
image. Therefore, the contour is attracted to pixels with large image gradients, i.e.
strong edges. At each iteration, the Wang method
'
guration
which minimizes the energy that corresponds to external forces and constraint
elements.
nds a new contour con
Search WWH ::




Custom Search