Journal
IEEE ACCESS
Volume 9, Issue -, Pages 27959-27970Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2021.3058267
Keywords
Diseases; Licenses; Training; Feature extraction; Numerical models; Neural networks; Kernel; Maize diseases identification; deep convolution neural networks; global pooling layer; inception module; transfer learning
Categories
Funding
- National Natural Science Foundation of China [31801753]
- JiLin provincial science and technology department international exchange and cooperation project [20200801014GH]
- [Jilin province education department 13th five-year'' science and technology research planning project [JJKH20200336KJ]
Ask authors/readers for more resources
In this study, a multi-scale convolutional global pooling neural network was proposed to improve the accuracy of maize disease identification. By enhancing the AlexNet model with additional convolutional layers and Inception modules, as well as replacing the fully-connected layer with a global pooling layer, the improved model showed better performance in recognizing maize diseases compared to other convolutional neural network models like VGGNet-16, DenseNet, ResNet-50, and AlexNet.
Deep learning is thought of as a promising mean to identify maize diseases. However, the drawback of deep learning is the huge sample data and low accuracy. In this paper, we proposed a multi-scale convolutional global pooling neural network to improve the accuracy of maize diseases identification. Firstly, on the basis of the AlexNet model, a convolutional layer and new Inception module are added to enhance the ability of AlexNet features extraction. Then, in order to avoid the over-fitting problem caused by too many parameters, we use the global pooling layer to replace the original fully-connected layer. Besides, we also adopt the transfer learning method to solve the over-fitting problem caused by insufficient sample data. The improved model can reduce over-fitting and epochs to enhance the performance of maize diseases recognition. From the considerable experimental results, we can conclude that the proposed model has better performance compared with convolutional neural network models VGGNet-16, DenseNet, ResNet-50 and AlexNet in recognition accuracy.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available