Deep Learning Architectures for Fruit and Leaf Disease Detection: A Critical Analysis of Methods, Metrics, Challenges, and Future Research Directions

Deep Learning Techniques for Citrus Disease Detection: A Comprehensive Review

Citrus crops are economically vital worldwide, yet they remain highly susceptible to a range of infectious diseases that cause considerable yield and quality losses each year. Early and accurate disease identification is fundamental to sustainable orchard management and food security. Over the past decade, deep learning has emerged as the dominant paradigm for automated plant disease detection, surpassing traditional image-processing pipelines in both accuracy and scalability. This paper presents a comprehensive review of deep learning methodologies applied to citrus disease detection, covering convolutional neural networks (CNNs), attention mechanisms, lightweight architectures, object detection frameworks, multimodal fusion, and edge-computing deployment. Recent studies are critically analyzed with respect to model architecture, dataset characteristics, performance metrics, and deployment context. The review identifies prevailing trends including the shift toward lightweight models for edge devices, the integration of attention modules for fine-grained feature capture, and the growing adoption of multimodal and transformer-based approaches. Key open challenges such as limited data diversity, computational constraints in field deployments, and the need for domain-adaptive models are also discussed, along with prospective research directions. The findings serve as a reference for researchers and practitioners seeking to develop robust, real-time citrus disease detection systems.

A Comprehensive Survey on Machine Learning and Deep Learning Approaches for Potato Leaf Disease Detection

A comprehensive and systematic review of state-of-the-art methods for detecting potato leaf disease, covering convolutional neural networks, transformer-based architectures, and hybrid models, and a strategic comparative analysis is conducted.

Deep Learning-based Bean Leaf Disease Classification: A Comparison of ResNet50 and VGG19

Background: Legumes, such as beans, are important in worldwide agriculture because of their nutritional value and soil-enriching qualities. However, bean crops are susceptible to diseases such as angular leaf spot and rust, which may reduce production and quality. Disease identification that is both effective and timely is essential to crop health and output. Traditional diagnostic approaches are often labor-intensive and susceptible to inaccuracy. Recent advances in deep learning (DL) provide interesting possibilities for automating disease categorization, possibly improving accuracy and efficiency. Methods: This study evaluates and compares the performance of two deep learning architectures, ResNet50 and VGG19, for the classification of bean leaf diseases. The dataset, sourced from Kaggle, comprises 1295 images categorized into three classes: Angular Leaf Spot, Rust and Healthy. Both systems relied on pre-trained ImageNet weights, with adjustments customized to the classification objective. The models were trained for 25 epochs and their performance was assessed based on overall accuracy. Result: The performance of the models is evaluated in terms of the confusion matrix, classification report and ROC(AUC) curves. The ResNet50 model achieved an overall accuracy of 93.75%, while the VGG19 model attained an accuracy of 91.41%. The findings indicate that ResNet50 performs better than VGG19 in terms of classification accuracy. This work demonstrates ResNet50’s performance for bean leaf disease classification tasks, providing important insights for future research and practical applications in agricultural disease control.

A Comparative Study of Deep Learning-Based Pest Detection Models with Interpretability and Deployment Strategies for Medicinal Plants

A comparative analysis of five deep learning models, namely Basic CNN, VGG16, ResNet50, VGG32, and the proposed CFNET, which is based on EfficientNetB3, for binary pest detection in medicinal plants confirms CFNET's suitability for mobile and edge-based agricultural monitoring systems.

A comparative study of deep learning models for tomato disease detection

Deep Learning Approaches for Apple Disease Classification and Detection: A PRISMA 2020 Systematic Literature Review

Apple diseases cause great losses in fruit yield and quality, while manual diagnosis is time-consuming, subjective, and difficult to scale across orchards. Deep learning has thus become a staple in image-based disease recognition, but evidence remains scattered across classification and object-detection paradigms, heterogeneous datasets, and inconsistent evaluation protocols. This systematic literature review integrates 30 peer-reviewed studies published between 2020 and 2026, selected from 180 database records using a PRISMA 2020-aligned protocol. The final corpus includes 22 image-classification studies and eight object-detection studies. One non-peer-reviewed preprint was kept as contextual evidence only and was excluded from all corpus counts and comparative analyses. Architectures, datasets, preprocessing and augmentation strategies, training configurations, evaluation metrics, evidence of generalization, and deployment characteristics are discussed separately for the two task paradigms. Reported classification accuracies vary from 91.0% to 99.99%, whereas detection studies report mAP@0.5 values from 82.1% to 99.99%; these ranges are descriptive and are not pooled estimates. These values are heavily dependent on dataset composition and evaluation design: controlled-background datasets often yield near-perfect scores, while field transfer can lead to a drop of almost 30 percentage points. CNNs still dominate the field, but hybrid transformer-based attention mechanisms, multi-scale feature fusion, class-imbalance-aware training, and lightweight YOLO variants are gaining traction. Long-standing limitations are the lack of reporting of hyperparameters, an over-reliance on accuracy, the lack of external validation, heterogeneity in annotation, the lack of uncertainty analysis, and limited reporting of latency, memory, and energy consumption. Accordingly, the research agenda emphasizes standardized real-orchard benchmarks, cross-dataset validation, calibrated and explainable predictions, reproducible experimental protocols, and deployment-aware model design.