Skip to main content

Table 6 Result obtained from dataset D1 (VGG-16Net)

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

Digit class

Precision

Recall

F1 score

Test samples

0

99.20

99.60

99.40

500

1

98.99

98.40

98.70

500

2

94.07

95.20

94.63

500

3

96.28

93.20

94.72

500

4

98.39

98.00

98.20

500

5

97.60

97.60

97.60

500

6

95.69

97.60

96.63

500

7

96.62

97.20

96.91

500

8

98.20

98.40

98.30

500

9

97.39

97.20

97.30

500

Overall recognition accuracy (%)

97.24