A VGG-19 Model with Transfer Learning and Image Segmentation for Classification of Tomato Leaf Disease

Hải, Nguyễn Thanh; Nguyen, Thanh-Nghia; Ngo, Ba-Viet

doi:10.3390/agriengineering4040056

Cited by 43 publications

(30 citation statements)

References 49 publications

(63 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The original data dimension of the workload in the identification experiment is [9,2500,18]. There are 9 groups of different load values, and each group of load experiments produces 2500 × 18 data points.…”

Section: Parameter Analysis Of Prediction Modelmentioning

confidence: 99%

“…Deep learning has been widely used in many fields, such as medical analysis [7,8], image recognition [9], structural analysis [4], target optimization [10,11], and so on. Although the process of machine learning is analogous to the learning process of the human brain, the exploration of its learning mechanism and the generalization ability of the model for unknown data still need to be relied on large sample data [12][13][14].…”

Section: Introduction 1motivationsmentioning

confidence: 99%

See 1 more Smart Citation

A workload identification method of industrial robot combining dynamic model and convolutional neural network

Yue,

Wang,

Zhang

et al. 2024

Eng. Res. Express

View full text Add to dashboard Cite

The motion joint system of industrial robot has obvious nonlinear characteristics, high dimensional running data and limited number of experimental samples. If mature neural network algorithm is used for identifying the workload of robots, it is easy to have over-learning problems, which seriously restricts the generalization ability of load identification method. In this paper, a load identification method combining the dynamic model of industrial robots with the neural network data model is proposed. A UR5 robot is used for carrying out multiple dynamic load testings to verify the effectiveness of the proposed identification method. Firstly, the workload identification by CNN algorithm is given, and the influence of parameters of prediction model and different neutral network are analyzed. Then the classical dynamic model of industrial robots with multi-degrees of freedom is established. The identified workload by dynamic model is also analyzed. At last, the deterministic information such as velocity and displacement is extracted from the calculation results of the dynamic model as the initial anchoring value. Then convolutional neural network is applied for compensating the residual highly nonlinear information. An improved mixing combination method is also proprosed. This method can effectively deal with the interaction of different types of information in the data, and preliminarily cooperate the dynamic model and convolutional neural network. This provides a basic framework and method for solving the problem of parameter identification in multi-degree-of-freedom systems with small samples.

show abstract

Section: Parameter Analysis Of Prediction Modelmentioning

confidence: 99%

Section: Introduction 1motivationsmentioning

confidence: 99%

A workload identification method of industrial robot combining dynamic model and convolutional neural network

Yue,

Wang,

Zhang

et al. 2024

Eng. Res. Express

View full text Add to dashboard Cite

show abstract

“…Among the various deep learning models, convolutional neural networks (CNNs) have emerged as the most widely used and effective models for plant disease detection. CNN models, such as Resnet [1], VGG [22], and AlexNet [34], have demonstrated superior performance in accurately classifying plant diseases. These models have been studied and fine-tuned to achieve high accuracy in disease classification tasks.…”

Section: Introductionmentioning

confidence: 99%

An Improved YOLOv5 for Accurate Detection and Localization of Tomato and Pepper Leaf Diseases

Tej,

Bouaafia,

Hajjaji

et al. 2024

Preprint

View full text Add to dashboard Cite

Agriculture serves as a vital sector in Tunisia, supporting the nation's economy and ensuring food production. However, the detrimental impact of plant diseases on crop yield and quality presents a significant challenge for farmers. In this context, computer vision techniques have emerged as promising tools for automating disease detection processes. This paper focuses on the application of the YOLOv5 algorithm for the simultaneous detection and localization of multiple plant diseases on leaves. By using a self-generated dataset and employing techniques such as augmentation, anchor clustering, and segmentation, the study aims to enhance detection accuracy. An ablation study comparing YOLOv5s and YOLOv5x models demonstrates the superior performance of YOLOv5x, achieving a mean average precision (mAP) of 96.5%.

show abstract

“…Many deep learning-based methods have been proposed for crop disease identification [5][6][7][8][9][10][11][12][13][14][15][16][17][18]. For example, li et al [5] proposed the OplusVNet, a 13-layer convolutional neural network that achieved 99% prediction accuracy on a dataset collected from the field using VGG16 network modules for transfer learning.…”

Section: Introductionmentioning

confidence: 99%

“…For example, li et al [5] proposed the OplusVNet, a 13-layer convolutional neural network that achieved 99% prediction accuracy on a dataset collected from the field using VGG16 network modules for transfer learning. Nguyen et al [6] proposed a neural network model that combines image segmentation with transfer learning, segments the image and uses HSV to extract the original leaf area and black background, and feeds it into a VGG-19 model for transfer learning, achieving an accuracy of 99.72%, with a training time of 275000s. These networks have effectively improved the recognition of crop diseases and pests.…”

Section: Introductionmentioning

confidence: 99%

LBFNet: A Tomato Leaf Disease Identification Model based on Three-Channel Attention Mechanism and Quantitative Pruning

Chen¹,

Wang²,

Peng³

et al. 2023

Preprint

View full text Add to dashboard Cite

The current neural networks for tomato leaf disease recognition have problems such as large model parameters, long training time, and low model accuracy. To solve these problems, a lightweight convolutional neural network LBFNet is proposed in this paper.First, a lightweight convolutional neural network LBFNet is established as the base model. Secondly, a three-channel attention mechanism module is introduced to learn the disease features in tomato leaf disease images and reduce the interference of redundant features. Finally, a cascade module is introduced to increase the depth of the model, solve the gradient descent problem, and reduce the loss caused by increasing the depth of the model. The quantized pruning technique is also used to further compress the model parameters and optimize the model performance. The results show that the LBFNet model achieves 99.06% accuracy on the LBFtomato dataset, with a training time of 996s and a single classification accuracy of over 94%. Further training using the saved weight file after quantized pruning makes the model accuracy reach 97.66%. Compared with the base model, the model accuracy was improved by 28%, and the model parameters were reduced by 96.7% compared with the traditional Resnet50. It was found that LBFNet can quickly and accurately identify tomato leaf diseases in complex environments, providing effective assistance to agricultural producers.

show abstract

A VGG-19 Model with Transfer Learning and Image Segmentation for Classification of Tomato Leaf Disease

Cited by 43 publications

References 49 publications

A workload identification method of industrial robot combining dynamic model and convolutional neural network

A workload identification method of industrial robot combining dynamic model and convolutional neural network

An Improved YOLOv5 for Accurate Detection and Localization of Tomato and Pepper Leaf Diseases

LBFNet: A Tomato Leaf Disease Identification Model based on Three-Channel Attention Mechanism and Quantitative Pruning

Contact Info

Product

Resources

About