Table 1.
Abbreviations appearing in this article.
Fig 1.
Flowchart of data enhancement and WG-MARNet framework.
Table 2.
Profile of sample images for nine types of diseases.
Fig 2.
Structure diagram of the WG-MARNet.
Table 3.
Parameter configuration of residual block in conv1-conv5 group.
Fig 3.
Conv2_ 1 parameter operation diagram.
Fig 4.
High and low frequency decomposition effect picture.
(a) Low Frequency Patch Images. (b) Higher Frequency Patch Images.
Fig 5.
Multi-scale feature fusion method based on task design.
Fig 6.
Multi-channel feature fusion process diagram.
Fig 7.
Attenuation factor introduction graph.
Fig 8.
Example of recognition results of northern leaf blight and common rust.
a. Northon leaf blight. b. Common rust.
Fig 9.
ANTH, TRT, SCR, CR, SLB, PHLS, DLS, PHRS and NLB represent Anthracnose leaf blight, Tropical rust, Southern maizerust, Common rust, Southern leaf blight, Phaeosp haeria leaf spot, Diplodia leaf streak, Physoderma brown spot and Northern leaf blight respectively; The darker diagonal values in figures represent the number of correct classifications and the recall rate of each category, respectively.
Fig 10.
Effect comparison chart of multi-scale feature fusion.
Table 4.
Scheme configuration of optimizer and activation function.
Fig 11.
The loss curves of different classification and detection algorithms varying with the iteration number.
Fig 12.
The precision curves of different classification and detection algorithms varying with the iteration number.
Table 5.
Comparison of the detection results for different classification and detection algorithms.
Table 6.
Experimental results of each component of the WG-MARNet.