Explainable Deep Neural Network Based Multiclass Classification of Tomato Leaf Disease: A Systematic Review

This paper presents a comprehensive systematic review of AI-based approaches for tomato leaf disease classification. Deep learning models, particularly CNN-based architectures, have demonstrated remarkable success in achieving high classification accuracy. However, their performance is often limited by dataset bias and lack of generalization to real-world conditions. The integration of explainable AI techniques has improved model transparency and interpretability, addressing one of the key challenges in deploying AI systems in agriculture. Despite these advancements, several issues remain, including limited availability of real-world datasets, computational constraints, and challenges in model deployment. Future research should focus on developing robust, lightweight, and interpretable models that can operate effectively in real-world environments. The integration of edge AI, multimodal learning, and advanced explainability techniques will play a crucial role in advancing the field. Overall, AI-based tomato leaf disease detection systems have significant potential to enhance agricultural productivity and sustainability. However, bridging the gap between laboratory performance and real-world deployment remains a critical challenge that must be addressed in future research.

[1] S. P. Mohanty, D. P. Hughes, and M. Salathé, “Using deep learning for image-based plant disease detection,” Frontiers in Plant Science, vol. 7, 2016. [2] S. Sladojevic, M. Arsenovic, A. Anderla, D. Culibrk, and D. Stefanovic, “Deep neural networks based recognition of plant diseases by leaf image classification,” Computational Intelligence and Neuroscience, 2016. [3] J. Too, S. Yujian, L. Njuki, and Y. Yingchun, “A comparative study of fine-tuning deep learning models for plant disease identification,” Computers and Electronics in Agriculture, vol. 161, pp. 272–279, 2019. [4] A. Kamilaris and F. X. Prenafeta-Boldú, “Deep learning in agriculture: A survey,” Computers and Electronics in Agriculture, vol. 147, pp. 70–90, 2018. [5] K. P. Ferentinos, “Deep learning models for plant disease detection and diagnosis,” Computers and Electronics in Agriculture, vol. 145, pp. 311–318, 2018. [6] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv:1409.1556, 2015. [7] A. Dosovitskiy et al., “An image is worth 16x16 words: Transformers for image recognition at scale,” ICLR, 2021. [8] H. Touvron et al., “Training data-efficient image transformers & distillation through attention,” ICML, 2021.                                                  [9] R. R. Selvaraju et al., “Grad-CAM: Visual explanations from deep networks via gradient-based localization,” ICCV, 2017. [10] M. T. Ribeiro, S. Singh, and C. Guestrin, “Why should I trust you? Explaining the predictions of any classifier,” KDD, 2016.