Identification of plant disease images via a squeeze‐and‐excitation MobileNet model and twice transfer learning

Chen, Junde; Zhang, Defu; Suzauddola,; Nanehkaran, Yaser Ahangari; Sun, Yuhao

doi:10.1049/ipr2.12090

Cited by 63 publications

(31 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In all cases, use of YMufT effectively enhanced the models' ability to classify images in both minor and major species. [27] 0.9523 0.9500 0.9500 0.9500 MobileNetV2 [28] 0.9350 0.9400 0.9400 0.9300 Figure 23 compares the number of images that were correctly classified using the conventional training method but incorrectly classified using YMufT (CtYf) and vice versa (CfYt). In all cases, use of YMufT effectively enhanced the models' ability to classify images in both minor and major species.…”

Section: Discussionmentioning

confidence: 99%

Yielding Multi-Fold Training Strategy for Image Classification of Imbalanced Weeds

et al. 2021

View full text Add to dashboard Cite

An imbalanced dataset is a significant challenge when training a deep neural network (DNN) model for deep learning problems, such as weeds classification. An imbalanced dataset may result in a model that behaves robustly on major classes and is overly sensitive to minor classes. This article proposes a yielding multi-fold training (YMufT) strategy to train a DNN model on an imbalanced dataset. This strategy reduces the bias in training through a min-class-max-bound procedure (MCMB), which divides samples in the training set into multiple folds. The model is consecutively trained on each one of these folds. In practice, we experiment with our proposed strategy on two small (PlantSeedlings, small PlantVillage) and two large (Chonnam National University (CNU), large PlantVillage) weeds datasets. With the same training configurations and approximate training steps used in conventional training methods, YMufT helps the DNN model to converge faster, thus requiring less training time. Despite a slight decrease in accuracy on the large dataset, YMufT increases the F1 score in the NASNet model to 0.9708 on the CNU dataset and 0.9928 when using the Mobilenet model training on the large PlantVillage dataset. YMufT shows outstanding performance in both accuracy and F1 score on small datasets, with values of (0.9981, 0.9970) using the Mobilenet model for training on small PlantVillage dataset and (0.9718, 0.9689) using Resnet to train on the PlantSeedlings dataset. Grad-CAM visualization shows that conventional training methods mainly concentrate on high-level features and may capture insignificant features. In contrast, YMufT guides the model to capture essential features on the leaf surface and properly localize the weeds targets.

show abstract

Section: Discussionmentioning

confidence: 99%

Yielding Multi-Fold Training Strategy for Image Classification of Imbalanced Weeds

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In [28], the authors investigated the detection and improvement of plant lesion features using transfer learning with deep CNN. The features of both MobileNet and squeeze-and-excitation network called SE-MobileNet helps to identify plant disease.…”

Section: Related Workmentioning

confidence: 99%

EfficientNet-Based Robust Recognition of Peach Plant Diseases in Field Images

Ahmad¹,

Khan²,

Irshad³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Plant diseases are a major cause of degraded fruit quality and yield losses. These losses can be significantly reduced with early detection of diseases to ensure their timely treatment, particularly in developing countries. In this regard, an expert system based on deep learning model where the expert knowledge, particularly the one acquired by plant pathologist, is recursively learned by the system and is applied using a smart phone application for use in the target field environment, is being proposed. In this paper, a robust disease detection method is developed based on convolutional neural network (CNN), where its powerful features extraction capabilities are leveraged to detect diseases in images of fruits and leaves. The features extraction pipelines of several state-of-the-art pretrained networks are fine-tuned to achieve optimal detection performance. A novel dataset is collected from peach orchards and extensively augmented using both label-preserving and non-label-preserving transformations. The augmented dataset is used to study the effects of finetuning the pretrained networks' feature extraction pipeline as opposed to keeping the network parameters unchanged. The CNN models, particularly EfficientNet exhibited superior performance on the target dataset once their feature extraction pipelines are fine-tuned. The optimal model is able to achieve 96.6% average accuracy, 90% sensitivity and precision, and 98% specificity on the test set of images.

show abstract

“…MobileNet Architecture proved its efficiency when applied on different domains [12]- [14], by constructing lightweight deep convolutional neural networks.…”

Section: B Mobilenet Architecturementioning

confidence: 99%

Welding Seam Classification in the Automotive Industry using Deep Learning Algorithms

Hachem

Perrot

Painvin

et al. 2021

2021 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)

View full text Add to dashboard Cite

Welding seam inspection is key process in the automotive industry and should guarantee the quality required by the client. Visual inspection is achieved by the operator who checks each part manually, making the reliability highly improvable. That's why automating the visual inspection is needed in today's production process. Collecting data from inside the plant may not provide a balanced number of images between good welding seams and bad welding seams. In this article, we will compare a standard deep learning algorithm applied on raw data with data augmentation approaches. Our target is to reach an accuracy of 97% on the defected reference parts. This target is reached on some welds, while it remains a challenge on other welds.

show abstract

Identification of plant disease images via a squeeze‐and‐excitation MobileNet model and twice transfer learning

Cited by 63 publications

References 31 publications

Yielding Multi-Fold Training Strategy for Image Classification of Imbalanced Weeds

Yielding Multi-Fold Training Strategy for Image Classification of Imbalanced Weeds

EfficientNet-Based Robust Recognition of Peach Plant Diseases in Field Images

Welding Seam Classification in the Automotive Industry using Deep Learning Algorithms

Contact Info

Product

Resources

About