Skip to main content

Table 3 The classification results of multiple view features using SVM

From: Automatic plankton image classification combining multiple view features via multiple kernel learning

Datasets

C

Gaussian

Polynomial

Linear

  

R

1−P

F measure

R

1−P

F measure

R

1−P

F measure

WHOI

1

84%

15.43%

0.843

88.97%

10.95%

0.89

86.45%

13.41%

0.865

 

10

88.94%

11%

0.89

89.45%

10.47%

0.895

88.12%

11.78%

0.882

 

100

89.57%

10.3%

0.896

88.42%

11.46%

0.885

86.33%

13.59%

0.864

ZooScan

1

79.65%

16.06%

0.817

82.45%

15.99%

0.832

79.91%

18.14%

0.809

 

10

85.39%

13.2%

0.861

84.14%

15.22%

0.845

85.52%

16.01%

0.847

 

100

84.87%

13.62%

0.856

83.04%

16.02%

0.835

82.27%

18.23%

0.82

Kaggle

1

77.26%

18.96%

0.791

77.48%

19.6%

0.789

71.32%

25.09%

0.731

 

10

82.41%

16.33%

0.83

80.7%

18.08%

0.813

78.44%

20.63%

0.789

 

100

82.09%

18.89%

0.816

79.01%

19.73%

0.796

78.1%

22.05%

0.78

  1. The entries in boldface indicate the best classification results with the highest F measure