Forest pest identification based on a new dataset and convolutional neural network model with enhancement strategy

•A new dataset of 67,953 images is constructed for forestry pest identification.•Graph-based Visual Saliency enhances the dataset.•Transfer learning and fine-tune are combined to build a twice transfer strategy in the Convolutional Neural Networks.•A new platform for forestry pest identification is...

Full description

Saved in:
Bibliographic Details
Published in:Computers and electronics in agriculture 2022-01, Vol.192, p.106625, Article 106625
Main Authors: Liu, Yang, Liu, Shuang, Xu, Jingwen, Kong, Xiangna, Xie, Liao, Chen, Keyu, Liao, Yunyuan, Fan, Bowei, Wang, Kaili
Format: Article
Language:English
Subjects:
Artificial neural networks
Classification
Dataset enhancement
Datasets
Deep learning
Forest pests
Identification platform
Image enhancement
Machine learning
Neural networks
New dataset
Pests
Twice transfer strategy
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•A new dataset of 67,953 images is constructed for forestry pest identification.•Graph-based Visual Saliency enhances the dataset.•Transfer learning and fine-tune are combined to build a twice transfer strategy in the Convolutional Neural Networks.•A new platform for forestry pest identification is developed. Due to the lack of samples, deep learning in forest pest identification is severely limited, and classification accuracy and generalization ability are insufficient. To address this issue, we have constructed a new dataset of forest pests containing 67,953 images, enhanced the dataset by Graph-based Visual Saliency, and combined transfer learning and fine-tune to build a twice transfer strategy in the convolutional neural networks (CNNs) for pest recognition. Based on the new dataset and developed model, a new platform for forest pest identification was finally built. Compared with prevalent models including Inception-V3, MobileNet-V2, ResNet-50-V2, InceptionResNet-V2, and Xception, our method improves the accuracy and generalization ability of classification by 6.2% and 7.0%, respectively. Meanwhile, class activation maps show that the model's focus on the target has also been increased by 9.0%. In general, the new proposed dataset and training strategy can greatly improve classification performance of CNNs, which may be helpful to the effective control on forest pests.
ISSN:0168-1699
1872-7107
DOI:10.1016/j.compag.2021.106625