```html Recent Advances in Machine and Deep Learning for Pomegranate Disease Detection and Classification: A Comprehensive Review | IJICCS

International Journal of Intelligent Communication and Computer Science

Peer Reviewed Scholarly Journal for Advanced Research

Recent Advances in Machine and Deep Learning for Pomegranate Disease Detection and Classification: A Comprehensive Review

Manya Awasthi1, Rajat Verma2

1 Research Scholar, Department of Computer Science and Engineering, Pranveer Singh Institute of Technology, Kanpur, Uttar Pradesh, India

2 Department of Computer Science and Engineering, Pranveer Singh Institute of Technology, Kanpur, Uttar Pradesh, India

India

Corresponding Author: Manya Awasthi

Email: awasthi.manyu12@gmail.com

Abstract

Pomegranate (Punica granatum L.) is an economically important fruit crop whose productivity and market value are significantly affected by fungal, bacterial, insect-related, and physiological disorders. Conventional disease identification mainly relies on visual inspection by farmers and agricultural experts, making the process subjective, time-consuming, labour-intensive, and difficult to scale. Recent advances in machine learning (ML), deep learning (DL), computer vision, transfer learning, and intelligent agricultural systems have enabled automated approaches for pomegranate disease detection and classification. This review provides a comprehensive analysis of ML- and DL-based techniques for pomegranate disease analysis, covering conventional feature-based classifiers, convolutional neural networks (CNNs), transfer-learning architectures, attention mechanisms, optimized deep networks, vision transformers, disease severity estimation, and emerging federated-learning approaches. Particular attention is given to datasets, image acquisition, preprocessing, augmentation, feature extraction, classification strategies, evaluation metrics, and deployment requirements. The review highlights the transition from conventional ML toward transfer learning, attention-based models, transformers, and privacy-preserving federated learning. Key challenges include limited dataset diversity, field-level generalization, disease severity assessment, explainability, data leakage, class imbalance, privacy, computational efficiency, and edge deployment. Finally, future directions involving multimodal learning, foundation models, generative augmentation, explainable AI, federated learning, and integrated disease-management systems are discussed to support robust and scalable pomegranate disease monitoring.

Keywords

Pomegranate ; plant disease detection; CNN, ; Tarnsfer Learning; Vision Transformer; disease classification

Full Text

The complete article is available in PDF format.

View / Download PDF

How to Cite

Manya Awasthi, and Rajat verma "Recent Advances in Machine and Deep Learning for Pomegranate Disease Detection and Classification: A Comprehensive Review" International Journal of Intelligent Communication and Computer Science, vol. 4, no. 1, 2026, pp. 1-21.

Copyright and Licensing

Beginning with Volume 4, articles published in IJICCS are licensed under the Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0).

The article may be shared and adapted for non-commercial purposes, provided appropriate credit is given to the original author(s) and IJICCS.

View CC BY-NC 4.0 License

```