A Deep Features Extraction Model Based on the Transfer Learning Model and Vision Transformer “TLMViT” for Plant Disease Classification

Abstract

This paper proposes a novel approach for extracting deep features and classifying diseased plant leaves. The agriculture industry is negatively impacted by plant diseases causing crop and economic loss. Accurate and timely diagnosis is crucial for managing and controlling plant diseases, as traditional methods can be costly and time-consuming. Deep learning-based tools effectively detect plant diseases depending on the qualitative of extracted features. In this regard, a hybrid model for plant disease classification based on a Transfer Learning-based model followed by a vision transformer (TLMViT) is proposed. TLMViT has four stages: 1) data acquisition, where the PlantVillage and wheat datasets are used to train and evaluate the proposed model, 2) image augmentation to increase the number of training samples and overcome the overfitting issue, 3) leaf feature extraction by two consecutive phases: initial features extraction by using pre-trained based model and deep features extraction by using ViT model, and 4) classification by using MLP classifier. TLMViT is experimented with using five pre-trained-based models followed by ViT individually. TLMViT performs accurately in plant disease classification, obtaining 98.81% and 99.86% validation accuracy for VGG19 followed by the ViT model on PlantVillage and wheat datasets respectively. Moreover, TLMViT is compared with pre-trained-based architecture. The comparison result illustrates that TLMViT achieved an enhancement of 1.11% and 1.099% in validation accuracy, 2.576% and 2.92% in validation loss compared with the transfer learning-based model for PlantVillage and wheat datasets respectively. Thereby proposed model proves the efficiency of using ViT for extracting deep features from the leaf.INDEX TERMS Plant disease, image processing, deep learning, transfer learning, vision transformer.

Artificial Intelligence: A Promising Tool for Application in Phytopathology

“…Other authors are making significant advances in developing models which are more advanced in capabilities and simpler in their handling, thanks to the evolution that vision systems and their conjunction with large language modeling systems are undergoing in recent months. In this line, Tabbakh and Barpanda [121] introduced an innovative hybrid model for the classification of plant diseases, through the integration of Transfer Learning with a Vision Transformer (TLMViT). This hybrid approach stands out for its unique ability to extract and analyze deep features of plant leaf images, achieving exceptionally high accuracy in the evaluated datasets.…”

“…The application of their model managed to achieve identification accuracies above 98%. This hybrid model, combining transferred learning with the power of vision transformers, illustrates a qualitative leap in the detection and classification of plant diseases, offering new perspectives for precision agriculture and sustainable crop management [121].…”

ViT-SmartAgri: Vision Transformer and Smartphone-Based Plant Disease Detection for Smart Agriculture

“…The Vision Transformer (ViT) model holds significance in addressing the unanswered questions in tomato leaf disease detection using deep learning: (i) ViT introduces a transformative approach by leveraging self-attention mechanisms, allowing the model to focus on relevant features without manual extraction. Its architecture inherently addresses the need for efficient automated feature extraction, potentially mitigating concerns about excluding vital information in the detection process [21]. (ii) ViT inherently incorporates attention mechanisms through its self-attention mechanisms.…”

Plant Leaf Disease Detection Using Resnet-50 Based on Deep Learning

“…Accurate and precise timing is necessary for plant disease administration and restraint, and traditional methodology are costly and consuming the time. In addition, plant diseases severely affect the agricultural industry, resulting in reduced crop yields and economic losses [5].…”