GSAtt-CMNetV3: Pepper Leaf Disease Classification Using Osprey Optimization

Begum, Shaik Salma Asiya; Syed, Hussain

doi:10.1109/access.2024.3358833

Cited by 4 publications

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, a Multi-channel Automatic Orientation Recurrent Attention Network (M-AORANet) was proposed to extract rich disease features, extract multi-scale fine features, and recycle them, and its recognition accuracy reached 96.47%. Begum, S et al [ 22 ] improved the contrast-limited adaptive histogram equalization (ICLAHE) technique to enhance image quality, and then used kernelized gravity-based density clustering (KGDC) to segment the lesion area. Finally, gated self-attention convolutional MobileNetV3 (GSAtt-CMNetV3) was used for feature extraction and classification, and the recognition accuracy reached 97.87%.…”

Section: Introductionmentioning

confidence: 99%

Identification of Pepper Leaf Diseases Based on TPSAO-AMWNet

Wan,

Zhu,

Dai

et al. 2024

Plants

View full text Add to dashboard Cite

Pepper is a high-economic-value agricultural crop that faces diverse disease challenges such as blight and anthracnose. These diseases not only reduce the yield of pepper but, in severe cases, can also cause significant economic losses and threaten food security. The timely and accurate identification of pepper diseases is crucial. Image recognition technology plays a key role in this aspect by automating and efficiently identifying pepper diseases, helping agricultural workers to adopt and implement effective control strategies, alleviating the impact of diseases, and being of great importance for improving agricultural production efficiency and promoting sustainable agricultural development. In response to issues such as edge-blurring and the extraction of minute features in pepper disease image recognition, as well as the difficulty in determining the optimal learning rate during the training process of traditional pepper disease identification networks, a new pepper disease recognition model based on the TPSAO-AMWNet is proposed. First, an Adaptive Residual Pyramid Convolution (ARPC) structure combined with a Squeeze-and-Excitation (SE) module is proposed to solve the problem of edge-blurring by utilizing adaptivity and channel attention; secondly, to address the issue of micro-feature extraction, Minor Triplet Disease Focus Attention (MTDFA) is proposed to enhance the capture of local details of pepper leaf disease features while maintaining attention to global features, reducing interference from irrelevant regions; then, a mixed loss function combining Weighted Focal Loss and L2 regularization (WfrLoss) is introduced to refine the learning strategy during dataset processing, enhancing the model’s performance and generalization capabilities while preventing overfitting. Subsequently, to tackle the challenge of determining the optimal learning rate, the tent particle snow ablation optimizer (TPSAO) is developed to accurately identify the most effective learning rate. The TPSAO-AMWNet model, trained on our custom datasets, is evaluated against other existing methods. The model attains an average accuracy of 93.52% and an F1 score of 93.15%, demonstrating robust effectiveness and practicality in classifying pepper diseases. These results also offer valuable insights for disease detection in various other crops.

show abstract

Section: Introductionmentioning

confidence: 99%

Identification of Pepper Leaf Diseases Based on TPSAO-AMWNet

Wan,

Zhu,

Dai

et al. 2024

Plants

View full text Add to dashboard Cite

show abstract

A Cutting Edge Deep Learning Models for Paddy Leaf Disease Detection and Classification

Dhanalakshmi,

Ponmozhi,

Ajmal

2024

2024 3rd International Conference on Artificial Intelligence for Internet of Things (AIIoT)

View full text Add to dashboard Cite

Research on the identification method of cable insulation defects based on Markov transition fields and transformer networks

Zhao,

Fang,

Wang

et al. 2024

Front. Phys.

View full text Add to dashboard Cite

Identifying cable insulation defects is crucial for preventing system failures and ensuring the reliability of electrical infrastructure. This paper introduces a novel method leveraging the Markov transition field (MTF) and Transformer network to improve the precision of cable insulation defect identification and enhance the algorithm's noise resistance. Firstly, the algorithm performs modal transformation on the time series data acquired by the ultrasonic probe through MTF, generating corresponding images. Following this, the image data are input into a pre-trained Transformer network to achieve automated feature extraction. Subsequently, a multi-head attention mechanism is introduced, which assigns weights to the features extracted by the Transformer network, thereby emphasizing the most critical information for the identification task. Finally, more accurate defect identification is achieved based on the weighted features. The results demonstrate that this method achieves higher accuracy and stronger noise resistance compared to traditional image processing and recognition methods, making it a robust solution for cable insulation defect identification.

show abstract

GSAtt-CMNetV3: Pepper Leaf Disease Classification Using Osprey Optimization

Cited by 4 publications

References 26 publications

Identification of Pepper Leaf Diseases Based on TPSAO-AMWNet

Identification of Pepper Leaf Diseases Based on TPSAO-AMWNet

A Cutting Edge Deep Learning Models for Paddy Leaf Disease Detection and Classification

Research on the identification method of cable insulation defects based on Markov transition fields and transformer networks

Contact Info

Product

Resources

About