The Prague Texture Segmentation Datagenerator and Benchmark - Results
optimized
for

Results are sorted by criterion 'RM' (root mean square proportion estimation error) in ascending order. The sorting criterium or the order can be changed by clicking on the appropriate criterium label. Subset of compared results can be filtered by several filters below. The segmentation details (single mosaics and their corresponding criteria values) are visible by clicking on the order number. Below the criterium labels are mean and standard deviation of the values of displayed results. They are used to compute z-scores which are displayed in brackets. The ranks are displayed in parentheses.

Select  result's set    benchmark     hidden results Show Hide
Filter by algorithm features
? 0 1   f1 = classification (supervised segmentation)
? 0 1   f2 = hiearchy result (manual selection)
? 0 1   f3 = known number of regions
? 0 1   f4 = [reserved]
Filter by degradationtype: ? no Gaussian Poisson Salt&pepper Blur (Gaussian) Median
Filter by algorithm
Algorithm: Version:

   
Benchmark - Colour f1 f2 f3 f4 AVG
RANK
NORM
CS
43.17
±2.85
OS
14.35
±0.40
US
27.03
±2.98
ME
19.38
±7.37
NE
18.10
±6.33
O
30.10
±5.01
C
37.46
±7.55
CA
58.10
±0.65
CO
68.94
±0.06
CC
71.91
±2.60
I
31.06
±0.06
II
8.10
±0.52
EA
65.87
±0.00
MS
55.66
±0.15
criterion 'RM' (root mean square proportion estimation error) in ascending orderRM
9.93
±1.03
CI
67.90
±0.55
GCE
14.38
±3.15
LCE
8.35
±0.64
BCE
40.49
±0.15
GBCE
34.45
±2.66
BGM
68.94
±0.06
SC
64.02
±0.10
SSC
62.10
±0.30
VD
18.68
±0.16
L
68.31
±1.65
AVI
7.62
±0.34
NVI
23.11
±1.97
NMI
66.74
±5.08
M
19.97
±3.70
ARI
57.01
±0.52
JC
54.42
±1.08
DC
68.08
±0.02
FMI
70.16
±0.81
WI
63.63
±1.78
WII
81.79
±2.22
NBDE
10.76
±2.33
 1.  rohit.iiith's Graph based Segmentation   [normal] 0 0 0 1  71.66 
 (1.44) 
 [0.111] 
40.32
(2)
[-1.000]
14.75
(2)
[1.000]
24.05
(1)
[-1.000]
26.74
(2)
[1.000]
24.43
(2)
[1.000]
25.10
(1)
[-1.000]
45.01
(2)
[1.000]
57.45
(2)
[-1.000]
69.00
(1)
[1.000]
74.51
(1)
[1.000]
31.00
(1)
[-1.000]
7.58
(1)
[-1.000]
65.86
(2)
[-1.016]
55.81
(1)
[1.000]
8.90
(1)
[-1.000]
68.46
(1)
[1.000]
17.54
(2)
[1.000]
8.99
(2)
[1.000]
40.34
(1)
[-1.000]
31.79
(1)
[-1.000]
69.00
(1)
[1.000]
64.12
(1)
[1.000]
61.80
(2)
[-1.000]
18.83
(2)
[1.000]
69.96
(1)
[1.000]
7.27
(1)
[-1.000]
21.14
(1)
[-1.000]
71.82
(1)
[1.000]
16.27
(1)
[-1.000]
57.53
(1)
[1.000]
53.34
(2)
[-1.000]
68.06
(2)
[-1.002]
69.35
(2)
[-1.000]
61.84
(2)
[-1.000]
79.58
(2)
[-1.000]
8.43
(1)
[-1.000]
 2.  yuanj's RS   [large] 0 0 0 1  71.87 
 (1.56) 
 [-0.111] 
46.02
(1)
[1.000]
13.96
(1)
[-1.000]
30.01
(2)
[1.000]
12.01
(1)
[-1.000]
11.77
(1)
[-1.000]
35.11
(2)
[1.000]
29.91
(1)
[-1.000]
58.75
(1)
[1.000]
68.89
(2)
[-1.000]
69.30
(2)
[-1.000]
31.11
(2)
[1.000]
8.63
(2)
[1.000]
65.87
(1)
[1.005]
55.52
(2)
[-1.000]
10.96
(2)
[1.000]
67.35
(2)
[-1.000]
11.23
(1)
[-1.000]
7.70
(1)
[-1.000]
40.64
(2)
[1.000]
37.11
(2)
[1.000]
68.89
(2)
[-1.000]
63.92
(2)
[-1.000]
62.40
(1)
[1.000]
18.52
(1)
[-1.000]
66.67
(2)
[-1.000]
7.96
(2)
[1.000]
25.08
(2)
[1.000]
61.66
(2)
[-1.000]
23.67
(2)
[1.000]
56.50
(2)
[-1.000]
55.50
(1)
[1.000]
68.10
(1)
[1.002]
70.97
(1)
[1.000]
65.41
(1)
[1.000]
84.01
(1)
[1.000]
13.09
(2)
[1.000]