Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Table 1.

Convolutional neural network related.

More »

Table 1 Expand

Table 2.

Traditional machine learning related.

More »

Table 2 Expand

Fig 1.

Forage grasses identification process.

More »

Fig 1 Expand

Fig 2.

Photos of herbage species.

More »

Fig 2 Expand

Fig 3.

Quantity before and after data balance for each type of forage grasses.

More »

Fig 3 Expand

Fig 4.

E-A-Net network structure.

More »

Fig 4 Expand

Fig 5.

Detailed structure of autoencoder network.

More »

Fig 5 Expand

Fig 6.

Data processing results: The first row is the original data, the second is the cutout enhanced data, and the third is the background segmentation data.

More »

Fig 6 Expand

Fig 7.

Loss curve of autoencoder network.

More »

Fig 7 Expand

Fig 8.

Comparison of active thermograms before and after background removal.

More »

Fig 8 Expand

Fig 9.

Training validation curve.

More »

Fig 9 Expand

Table 3.

Train and validation results analysis.

More »

Table 3 Expand

Fig 10.

The influence of edge information on model recognition.

(a) Feature maps output by a Sobel operator, (b) Feature maps of the first three pooling layers of the network extracted for edges, (c) Extracting network feature map for class-activated edges.

More »

Fig 10 Expand

Fig 11.

The influence of autoencoding network on the overall model.

(a) Image input to autoencoder network, (b) Result of last two convolutional layers and last pooling layer of autoencoder network, (c) Class activation E-A-Net autoencoder network partial characteristic diagram, (d) Class activation basic neural network thermogram.

More »

Fig 11 Expand

Fig 12.

Confusion matrix diagram: Where the horizontal axis of the confusion matrix is the real type and the vertical axis is the prediction type.

On the first line is the confusion matrix for VGG16 [51], ResNet50 [38], and EfficientNetB0 [52] networks, and on the second line is the confusion matrix for E-A-VGG16 and E-A-ResNet50, E-A-EfficientNetB0 networks.

More »

Fig 12 Expand

Table 4.

Test result.

More »

Table 4 Expand