Deep Transformer-Based Visual Framework for Early Detection of Plant Leaf Pathologies

A Deep Hybrid Convolutional Neural Network (CNN)–Transformer Approach for Early Detection of Tomato Leaf Diseases

A deep hybrid Convolutional Neural Network –Transformer architecture is introduced by combining ConvNeXt Large (ConvNeXt-L) and Swin Transformer architecture by combining ConvNeXt Large (ConvNeXt-L) and Swin Transformer (as local feature extractor) and Swin Transformer (as global context encoder) to predict tomato leaf diseases.

ADVANCING PLANT DISEASE DETECTION THROUGH STATE-OF-THE-ART DEEP LEARNING MODELS LEVER-AGING EFFICIENTNETV2, VISION TRANSFORMER, AND ENSEMBLE TECHNIQUES

Plant diseases are still posing a challenge to the productivity, quality of crops, and food security, especially in locations where field diagnosis is based on manual visual inspec-tion. This paper assesses deep learning network-based automated classification of plant leaf diseases on public RGB leaf-image datasets, such as the Kaggle New Plant Diseases Dataset (Augmented) and PlantVillage images. They investigated four archi-tectures: EfficientNetV2B0, ResNet152V2, DenseNet201, and one hybrid Vision Trans-former (ViT)-based model. The steps of the experiment involved loading the dataset, exploratory analysis, preprocessing, resizing, normalizing, augmentation, transfer learning, independent model training, and evaluation metrics such as accuracy, preci-sion, recall, F1-score, training curves, testing results, and confusion matrices. The hy-brid ViT-based model was reported to have the best accuracy of 99.5%. On the smaller seven class subset of PlantVillage, EfficientNetV2B0 scored 98.11%. On the 38-class dataset, DenseNet201 improved test accuracy (97.34) and validation classification ac-curacy (around 98). ResNet152V2 scored 97.01 on the 38-class test set. The results demonstrate that CNN and transformer-based models can help to recognize plant diseases accurately whereas hybrid attention-based structures provide a promising path to enhance fine-grained classification. Since the model notebooks had varying class settings and splits, the comparison is seen as a model-structured assessment as opposed to a precisely identical benchmark across all architectures.

ViTRes: Vision Transformer and ResNet-Based FusionNet for Rice Leaf Disease Detection System

Real-Time Crop Disease Detection using Lightweight Vision Transformers (ViTs) on Drones

Accurate and efficient plant disease detection is crucial for precision agriculture to help minimize yield losses. Nevertheless, existing deep learning models are computationally resource-intensive, making them unsuitable for real-time monitoring with drones. In this work, we propose a lightweight vision transformer with a token pruning and knowledge distillation approach to detect plant diseases. We follow a teacher-student architecture where a vision transformer with complete feature learning ability serves as a teacher model and guides a student vision transformer. Attention-based token pruning helps prune out unimportant patch tokens from the student network during transformer layers and decreases computational redundancy without removing disease-relevant tokens. The proposed approach is evaluated on the PlantVillage color dataset with 54,305 images belonging to 38 classes (disease and healthy). Our experimental study shows that the proposed Student Vision Transformer network achieves a remarkable accuracy score of 96.47% and a macro F1-score of 95.30%, using only 1.28 million parameters. Moreover, our approach decreases the number of parameters by 61%. Our robustness tests under various transformations demonstrate the applicability of our vision transformer with pruning and knowledge distillation for real-time drone-assisted crop disease monitoring.

A Deep Transfer Learning Framework Using Pre-Trained CNN Architectures to Classify Tomato Leaf Diseases

Farmers produce a lot of tomatoes, hence early identification and tomato leaf disease diagnosis can increase production. The information used in this research is public ally available tomato leaf image dataset with multiple disease classifications to create and improve the model. This work employs a methodical preparation workflow that includes picture scaling, normalization, and augmentation to increase resilience to variations in illumination, background clutter, and leaf texture. Two improved deep learning models, Residual and MobileNetV2, the processed pictures to enable efficient mining of significant spatial and texture information related to illness patterns. The experiment's results demonstrate the framework's utility and reliability: MobileNetV2 showed precision of 95.11, accuracy of 95.01, F1 of 95.00, and recall of 95.01 in contrast. The residual model showed 97.76 accuracy, 97.78 precision, 97.76 recall, and 97.64 F1. For every evaluation metric, these perform better than conventional DL architectures like VGG16, CNN, and ResNet. impacting early identification and improved agricultural performance.

Advanced Deep Learning Approaches for Image-based Diagnosis of Banana Leaf Diseases

The state-of-the-art deep learning methods for detection and classification are applied on banana leaf dataset and healthy and two common diseases of banana leaves are classified in this work.