Skip to main content

Table 7 Result obtained from dataset D2 (VGG-19Net)

From: Ensemble of deep learning and machine learning approach for classification of handwritten Hindi numerals

Digit class

Precision

Recall

F1 score

Test samples

0

99.60

99.60

99.60

500

1

97.60

97.80

97.70

500

2

94.29

92.40

93.33

500

3

94.25

95.00

94.62

500

4

98.02

99.20

98.61

500

5

98.59

97.80

98.19

500

6

95.83

96.60

96.22

500

7

98.41

98.80

98.60

500

8

99.20

98.60

98.90

500

9

96.00

96.00

96.00

500

Overall recognition accuracy (%)

97.18