Skip to main content

Table 4 Comparative analysis of EggCountAI, ICount, and MECVision based on macro images of Ae. aegypti eggs

From: EggCountAI: a convolutional neural network-based software for counting of Aedes aegypti mosquito eggs

Image

Ground truth

EggCountAI

ICount

MECVision

1

2377

2185

1693

731

2

1579

1544

1346

1085

3

1821

1775

1489

924

4

1416

1391

1155

543

5

1490

1439

1318

746

6

2126

2112

1829

1259

7

1748

1724

1539

1122

8

1047

1041

932

503

9

3658

3344

2874

1831

10

1611

1575

1344

1016

Overall accuracy %

 

96.06%

82.22%

51.71%

Mean absolute error

 

74.30

335.40

911.30

Correlation

 

0.99

0.98

0.82

R-squared

 

0.99

0.97

0.67