Computational Intelligence - February 2013 - 44
togram features were extracted from 49
uniformly distributed bins in the HS space.
The object templates contain histogram
features from the training data set. A color
histogram of a search window was compared with these templates using the histogram intersection (HI) criterion. Table 4
shows the detection results. Overall, the
results indicate that the proposed system
achieves better perfor mance than the
H-TM method. Another disadvantage of
the H-TM method is that the memory required to store the
MDSOFN is an FC that is learned via neural learning.
templates is enormous.
Table 3 shows the detection results of different classifiers in
The second method used for comparison was from the
experiments 1 to 5. The results show that the training perforfree open-source computer vision library (OpenCV) [11].
mances of different classifiers are similar. The FC-SSCSVM
The OpenCV detection method uses simple Haar-like feashows better test results (higher DRs and precisions) than the
tures and a cascade of boosted tree classifiers as its statistical
SVM, the SOTFN-SV, and the FS-FCSVM in all experimodel. The number of stages was set to 25, and more than
ments. The FC-SSCSVM shows better test results than the
two hundred weak classifiers were generated in each experiMLP in experiments 1, 2, 4, and 5 and a result comparable to
ment. Table 4 shows the detection results, which were poor.
that of the MLP in experiment 3. The FC-SSCSVM shows
The major reason for these poor results is that the nonbetter test results than the MDSOFN in experiments 2 to 5
homogeneous color distribution in object appearance makes
and a result comparable to that of the MDSONFN in experiit difficult to extract a common Haar-like feature for the
ment 1. The MDSONFN uses Takagi-Sugeno-type fuzzy
same object with different views. Another reason is that a
rules, where the consequent part is a linear combination of
huge number of training patterns is required for a boosted
the input variables. The results show that the FC-SSCSVM
tree classifier to obtain good performance.
achieves a smaller model size (the total number of parameters)
The third method used for comparison was the scalethan the MDSONFN.
invariant feature transform (SIFT) method [12]. Though the
SIFT method extracts key points from a gray image, it
C. Comparisons with Other Object Detection Methods
has been successfully applied to detect objects in color images
The performance of the FC-SSCSVM was compared to
[39, 40]. The training objects in each experiment were used as
those of four different detection methods. The first one used
templates for key point localization. Table 4 shows the detecfor comparison was histogram-based template matching
tion results. The cup and notebook contain many more inten(H-TM) [2]. This method extracts color features for the
sive key points than the other objects, and thus, their DR is
detection of a specific object. In the experiments, color hishigher than those of the other
objects. The key points in the toy are
Table 4 Detection results of different methods in five experiments. The best result of Dr
so sparse that the SIFT method fails
and precision in different methods are shown in boldface.
to detect the toy in almost all of the
test images. The results shows that
proposed
MeThods
h-TM [2]
openCV [11] sIFT [12]
TFs-sVMpC [4] MeThod
the proposed method outperforms
the SIFT method.
90.40
Exp. 1
prEcision (%) 81.57
4.96
61.55
89.43
(60)
(FA numbEr)
(122)
(10588)
(258)
(70)
The fourth method used for
Dr
94.12
85.85
87.92
65.66
89.83
comparison uses a TS-type fuzzy
system learned through an SVM in
72.04
Exp. 2
prEcision (%) 58.02
3.56
54.29
69.92
(59)
(FA numbEr)
(110)
(4115)
(128)
(74)
principal component space (TFSDr
81.72
89.78
90.86
91.40
92.47
SVMPC) as a classifier [4]. In this
method, 49-dimensional global
Exp. 3
prEcision (%) 44.90
2.70
49.17
48.43
82.70
(FA numbEr)
(273)
(5835)
(183)
(213)
(50)
color histograms from 49 non-uni95.6
Dr
89
64.8
70.8
80
formly partitioned grids in an HS
space were first fed as inputs to a
73.36
Exp. 4
prEcision (%) 60.48
2.34
65.31
68.94
(69)
(FA numbEr)
(115)
(4805)
(94)
(73)
TFS-SVMPC to generate candi95
Dr
88
57.5
88.5
81
dates. Ten-dimensional HS values
from five locally partitioned regions
76.49
Exp. 5
prEcision (%) 45.18
3.48
1.88
69.38
(59)
(FA numbEr)
(216)
(4547)
(314)
(79)
in an object candidate were then fed
96
Dr
89
82
3
89.5
as inputs to another TFS-SVMPC
For the two proposed entropy features, the single
EEC value used in filtering phase one enables rapid
filtering via comparison against a threshold. The EGCD
feature vector in filtering phase two considered the
geometric distributions of the clustered composing
colors of an object and therefore reduced the number
of FAs and improved detection performance.
44
IEEE ComputatIonal IntEllIgEnCE magazInE | FEbruary 2013
Table of Contents for the Digital Edition of Computational Intelligence - February 2013
Computational Intelligence - February 2013 - Cover1
Computational Intelligence - February 2013 - Cover2
Computational Intelligence - February 2013 - 1
Computational Intelligence - February 2013 - 2
Computational Intelligence - February 2013 - 3
Computational Intelligence - February 2013 - 4
Computational Intelligence - February 2013 - 5
Computational Intelligence - February 2013 - 6
Computational Intelligence - February 2013 - 7
Computational Intelligence - February 2013 - 8
Computational Intelligence - February 2013 - 9
Computational Intelligence - February 2013 - 10
Computational Intelligence - February 2013 - 11
Computational Intelligence - February 2013 - 12
Computational Intelligence - February 2013 - 13
Computational Intelligence - February 2013 - 14
Computational Intelligence - February 2013 - 15
Computational Intelligence - February 2013 - 16
Computational Intelligence - February 2013 - 17
Computational Intelligence - February 2013 - 18
Computational Intelligence - February 2013 - 19
Computational Intelligence - February 2013 - 20
Computational Intelligence - February 2013 - 21
Computational Intelligence - February 2013 - 22
Computational Intelligence - February 2013 - 23
Computational Intelligence - February 2013 - 24
Computational Intelligence - February 2013 - 25
Computational Intelligence - February 2013 - 26
Computational Intelligence - February 2013 - 27
Computational Intelligence - February 2013 - 28
Computational Intelligence - February 2013 - 29
Computational Intelligence - February 2013 - 30
Computational Intelligence - February 2013 - 31
Computational Intelligence - February 2013 - 32
Computational Intelligence - February 2013 - 33
Computational Intelligence - February 2013 - 34
Computational Intelligence - February 2013 - 35
Computational Intelligence - February 2013 - 36
Computational Intelligence - February 2013 - 37
Computational Intelligence - February 2013 - 38
Computational Intelligence - February 2013 - 39
Computational Intelligence - February 2013 - 40
Computational Intelligence - February 2013 - 41
Computational Intelligence - February 2013 - 42
Computational Intelligence - February 2013 - 43
Computational Intelligence - February 2013 - 44
Computational Intelligence - February 2013 - 45
Computational Intelligence - February 2013 - 46
Computational Intelligence - February 2013 - 47
Computational Intelligence - February 2013 - 48
Computational Intelligence - February 2013 - 49
Computational Intelligence - February 2013 - 50
Computational Intelligence - February 2013 - 51
Computational Intelligence - February 2013 - 52
Computational Intelligence - February 2013 - 53
Computational Intelligence - February 2013 - 54
Computational Intelligence - February 2013 - 55
Computational Intelligence - February 2013 - 56
Computational Intelligence - February 2013 - 57
Computational Intelligence - February 2013 - 58
Computational Intelligence - February 2013 - 59
Computational Intelligence - February 2013 - 60
Computational Intelligence - February 2013 - 61
Computational Intelligence - February 2013 - 62
Computational Intelligence - February 2013 - 63
Computational Intelligence - February 2013 - 64
Computational Intelligence - February 2013 - 65
Computational Intelligence - February 2013 - 66
Computational Intelligence - February 2013 - 67
Computational Intelligence - February 2013 - 68
Computational Intelligence - February 2013 - 69
Computational Intelligence - February 2013 - 70
Computational Intelligence - February 2013 - 71
Computational Intelligence - February 2013 - 72
Computational Intelligence - February 2013 - 73
Computational Intelligence - February 2013 - 74
Computational Intelligence - February 2013 - 75
Computational Intelligence - February 2013 - 76
Computational Intelligence - February 2013 - 77
Computational Intelligence - February 2013 - 78
Computational Intelligence - February 2013 - 79
Computational Intelligence - February 2013 - 80
Computational Intelligence - February 2013 - Cover3
Computational Intelligence - February 2013 - Cover4
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202311
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202308
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202305
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202302
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202211
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202208
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202205
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202202
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202111
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202108
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202105
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202102
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202011
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202008
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202005
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202002
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201911
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201908
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201905
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201902
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201811
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201808
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201805
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201802
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter17
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall17
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_summer17
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_spring17
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter16
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall16
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_summer16
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_spring16
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter15
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall15
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_summer15
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_spring15
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter14
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall14
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_summer14
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_spring14
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter13
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall13
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_summer13
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_spring13
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter12
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall12
https://www.nxtbookmedia.com