Convolutional Rebalancing Network for the Classification of Large Imbalanced Rice Pest and Disease Datasets in the Field

Yang, Guofeng; Chen, Guipeng; Liu, Cong; JiangFan, Fu; Guo, Yang; Hua, Liu

doi:10.3389/fpls.2021.671134

Cited by 14 publications

(11 citation statements)

References 58 publications

(80 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Owing to the habits and diversity of pests, the long-tailed phenomenon is particularly common in pest datasets. Many studies tackled the long-tailed distribution of pest datasets [23], [24]. Wang et al [23] proposed a dynamic feature weighting method to re-weight head and tail classes based on feature centroids.…”

Section: Related Workmentioning

confidence: 99%

“…GAEnsemble [15] used a genetic algorithm to integrate prediction probabilities of multiple models. CRN [24] proposed a novel convolutional rebalancing network to solve the problem of unbalanced distribution. The accuracy of CRN was improved by 3.29% compared with GAEnsemble.…”

Section: ) Performance Comparisonmentioning

confidence: 99%

“…With the development of CNN, image-related work tends to use CNN to extract features. So we mainly used CNN and compared methods related to [20] 56.48 --FusionSum [21] 61.93 --GAEnsemble [15] 67.13 65.76 -CRN [24] 70.42 --Nanni et al [5] 73.62 --Ung et al [16] 74 CNN. Therefore, traditional machine learning methods are not considered.…”

Section: ) Performance Comparisonmentioning

confidence: 99%

See 2 more Smart Citations

MS-ALN: Multiscale Attention Learning Network for Pest Recognition

et al. 2022

View full text Add to dashboard Cite

Complex backgrounds, occlusions, and non-uniform classes present great challenges to pest recognition in practical applications. In this paper, we propose a multiscale attention learning network to address these problems. This network recursively locates discriminative regions and learns region-based feature representation in four branches. Three newly designed modules, which are target localization, attention detection, and attention removal connect two feature extracting sub-networks in adjacent branches to generate images of different scales. The target localization and attention detection modules locate the discriminative regions to filter out complex backgrounds while the attention removal module randomly removes the discriminative region to encourage the model to tackle occlusions. Thereafter, the parametershared classification sub-network follows the feature extracting sub-network in every branch for pest recognition. A decoupled learning strategy is adopted to address the problem of non-uniform classes. We experimented on the widely used IP-102 dataset and achieved state-of-the-art performance.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: ) Performance Comparisonmentioning

confidence: 99%

Section: ) Performance Comparisonmentioning

confidence: 99%

See 1 more Smart Citation

MS-ALN: Multiscale Attention Learning Network for Pest Recognition

et al. 2022

View full text Add to dashboard Cite

show abstract

“…With the breakthrough of hardware technology, deep learning (DL; Bengio et al, 2017 ) became the mainstream data processing method in recent years. Among many DL approaches, the convolutional neural network (CNN) is the most popular and representative one in computer vision and imaging processing communities ( Ioffe and Szegedy, 2015 ; Simonyan and Zisserman, 2015 ; Szegedy et al, 2015 ; He et al, 2016 ; Krizhevsky et al, 2017 ; Wang et al, 2021 ; Yang et al, 2021 ). Different from ML methods, CNN can integrate feature derivation, feature learning, and classifier into a single architecture.…”

Section: Introductionmentioning

confidence: 99%

Plant Species Classification Based on Hyperspectral Imaging via a Lightweight Convolutional Neural Network Model

et al. 2022

View full text Add to dashboard Cite

In recent years, many image-based approaches have been proposed to classify plant species. Most methods utilized red green blue (RGB) imaging materials and designed custom features to classify the plant images using machine learning algorithms. Those works primarily focused on analyzing single-leaf images instead of live-crown images. Without considering the additional features of the leaves’ color and spatial pattern, they failed to handle cases that contained leaves similar in appearance due to the limited spectral information of RGB imaging. To tackle this dilemma, this study proposes a novel framework that combines hyperspectral imaging (HSI) and deep learning techniques for plant image classification. We built a plant image dataset containing 1,500 images of 30 different plant species taken by a 470–900 nm hyperspectral camera and designed a lightweight conventional neural network (CNN) model (LtCNN) to perform image classification. Several state-of-art CNN classifiers are chosen for comparison. The impact of using different band combinations as the network input is also investigated. Results show that using simulated RGB images achieves a kappa coefficient of nearly 0.90 while using the combination of 3-band RGB and 3-band near-infrared images can improve to 0.95. It is also found that the proposed LtCNN can obtain a satisfactory performance of plant classification (kappa = 0.95) using critical spectral features of the green edge (591 nm), red-edge (682 nm), and near-infrared (762 nm) bands. This study also demonstrates the excellent adaptability of the LtCNN model in recognizing leaf features of plant live-crown images while using a relatively smaller number of training samples than complex CNN models such as AlexNet, GoogLeNet, and VGGNet.

show abstract

“…In various detection tasks in agriculture, deep learning combined with machine vision has been widely used in plant disease and pest identification, such as wheat blast image classification ( Fernández-Campos et al, 2021 ), rice disease and insect pest image classification ( Yang et al, 2021 ), plant leaf disease classification ( Gupta, 2017 ); plant variety identification, such as vegetable and fruit classification ( Zhu et al, 2018 ; Steinbrener et al, 2019 ), rapeseed variety classification ( Jung et al, 2021 ); crop quality detection, such as corn seed defect detection ( Wang et al, 2022 ); fruit crop rapid sorting system research, such as citrus online sorting system( Chen et al, 2021 ), and so on.…”

Section: Introductionmentioning

confidence: 99%

Tobacco shred varieties classification using Multi-Scale-X-ResNet network and machine vision

et al. 2022

View full text Add to dashboard Cite

The primary task in calculating the tobacco shred blending ratio is identifying the four tobacco shred types: expanded tobacco silk, cut stem, tobacco silk, and reconstituted tobacco shred. The classification precision directly affects the subsequent determination of tobacco shred components. However, the tobacco shred types, especially expanded tobacco silk and tobacco silk, have no apparent differences in macro-scale characteristics. The tobacco shreds have small size and irregular shape characteristics, creating significant challenges in their recognition and classification based on machine vision. This study provides a complete set of solutions aimed at this problem for screening tobacco shred samples, taking images, image preprocessing, establishing datasets, and identifying types. A block threshold binarization method is used for image preprocessing. Parameter setting and method performance are researched to obtain the maximum number of complete samples with acceptable execution time. ResNet50 is used as the primary classification and recognition network structure. By increasing the multi-scale structure and optimizing the number of blocks and loss function, a new tobacco shred image classification method is proposed based on the MS-X-ResNet (Multi-Scale-X-ResNet) network. Specifically, the MS-ResNet network is obtained by fusing the multi-scale Stage 3 low-dimensional and Stage 4 high-dimensional features to reduce the overfitting risk. The number of blocks in Stages 1–4 are adjusted from the original 3:4:6:3 to 3:4:N:3 (A-ResNet) and 3:3:N:3 (B-ResNet) to obtain the X-ResNet network, which improves the model’s classification performance with lower complexity. The focal loss function is selected to reduce the impact of identification difficulty for different sample types on the network and improve its performance. The experimental results show that the final classification accuracy of the network on a tobacco shred dataset is 96.56%. The image recognition of a single tobacco shred requires 103 ms, achieving high classification accuracy and efficiency. The image preprocessing and deep learning algorithms for tobacco shred classification and identification proposed in this study provide a new implementation approach for the actual production and quality detection of tobacco and a new way for online real-time type identification of other agricultural products.

show abstract

Convolutional Rebalancing Network for the Classification of Large Imbalanced Rice Pest and Disease Datasets in the Field

Cited by 14 publications

References 58 publications

MS-ALN: Multiscale Attention Learning Network for Pest Recognition

MS-ALN: Multiscale Attention Learning Network for Pest Recognition

Plant Species Classification Based on Hyperspectral Imaging via a Lightweight Convolutional Neural Network Model

Tobacco shred varieties classification using Multi-Scale-X-ResNet network and machine vision

Contact Info

Product

Resources

About