The agri-menace of plant diseases is a major chal- lenge to the world. cultural unproductiveness, which translates into massive economic losses, poorer quality of crop, and higher chances of food insecurity [5]. The conventional methods of identi- fying diseases rely on. visual inspection carried out by trained agricultural inspection. experts [6]. These methods, though useful in some situations, are not effective. are slow, and frequently laborious, and expensive, and exposed to in- such discrepancies caused by human tiredness or personal decision [6]. To by addressing these constraints, the given paper introduces a Deep learning- Plant Disease Detection System is an automated system that is intended to detect plant diseases. and correctly identify illnesses using images of plant leaves [1], [2]. The system makes use of Convo- lutional Neural Networks (CNNs), a class. of profound learning models that are highly image-recognitive. learn, to extract dis- criminative characteristics out of large sets of. annotated leaf images [7], [10]. The suggested framework includes image pre-processing, feature extraction, and so on. classification of diseases, and ultimate prediction, which allows effective end- to-end analysis [1]. This study gives a detailed analysis. of system architecture, methodology, used datasets, and execution procedure. Moreover, it talks about chal- challenges associated with variability of datasets, environmental and model generalization, and prospects of future research. to incorporate the system into the real-life smart farming. environments [4], [19].

This study introduced a Deep Learning-based Plant Disease Detection System that uses leaf images to accurately identify several plant diseases[1],[2]. High accuracy, robust generalization, and effective computational performance were attained by the system through the use of Convolutional Neural Networks and transfer learning architectures like MobileNetV2 and ResNet50[8],[9],[10]. Prediction reliability was greatly increased under a variety of input conditions by combining preprocessing meth- ods, data augmentation, and a strong training pipeline[15],[10]. The suggested system outperforms conventional machine-learning techniques and offers quick, reliable, and expert-level disease diagnosis, according to experimental results[16]. The model is ideal for use in agricultural settings because of its real-time disease detection capabilities and compatibility with web and mobile interfaces[19]. Additionally, Grad-CAM visualizations incorporate explainability mechanisms that im- prove transparency and help end users comprehend how the model makes decisions[14]. All things considered, the system could help farmers identify diseases early, lower crop losses, and improve precision farming techniques[19]. The proposed plant disease detection system provides a strong foundation for intelligent crop monitoring; however, several opportunities remain for expansion and enhance- ment.In order to enable more precise disease forecasting, future research may concentrate on integrating the system with IoT-based sensor networks to combine visual leaf anal- ysis with environmental data like temperature, humidity, and soil conditions[19]. The model can also be expanded to include additional crops, disease types, and field-captured datasets to improve robustness under real-world conditions[16]. Incorporating drone-based imaging would allow large-scale, automated farm surveillance, while deploying optimized lightweight models on smartphones would support offline diagnosis for farmers in remote areas[18],[19]. Further advancements could include disease severity esti- mation, automated treatment recommendations, and the use of advanced domain adaptation techniques to handle background variations and lighting inconsistencies[17]. Additionally, develop- ing user interfaces in multiple regional languages would enhance accessibility and increase adoption in rural agricultural communities[19]. Overall, these future extensions can transform the system into a comprehensive precision agriculture tool capable of assisting farmers throughout the crop lifecycle[4],[19].

[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, pp. 1–10, 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, vol. 2016, Article ID 3289801, 2016. [3] D. Hughes and M. Salathé, “An open access repository of images on plant health to enable the development of mobile disease diagnostics,” PlantVillage, 2015. [4] A. Kamilaris and F. X. Prenafeta-Boldú, “Deep learning in agriculture: A survey,” Computers and Electronics in Agriculture, vol. 147, pp. 70pp–90, 2018. [5] Food and Agriculture Organization of the United Nations (FAO), “Plant pests and diseases: Global impacts and responses,” FAO Report, Rome, Italy, 2021. [6] J. P. Monteiro, A. C. Oliveira, and R. S. Silva, “Limitations of manual plant disease diagnosis in large-scale agriculture,” Journal of Agricultural Science, vol. 9, no. 3, pp. 45–52, 2017. [7] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015. [8] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556, 2014. [9] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778. [10] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “MobileNetV2: Inverted residuals and linear bottlenecks,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 4510–4520. [11] X. Zhang, Y. Qiao, F. Meng, C. Fan, and M. Zhang, “Identification of maize leaf diseases using improved deep convolutional neural networks,” IEEE Access, vol. 6, pp. 30370–30377, 2018. [12] S. Phadikar and J. Sil, “Rice disease identification using pattern recognition techniques,” in Proceedings of the 11th International Conference on Computer and Information Technology (ICCIT), 2008, pp. 420–423. [13] S. Arivazhagan, R. N. Shebiah, S. Ananthi, and S. Vishnu Varthini, “Detection of unhealthy region of plant leaves and classification of plant leaf diseases using texture features,” Agricultural Engineering International: CIGR Journal, vol. 15, no. 1, pp. 211–217, 2013. [14] R. R. Selvaraju et al., “Grad-CAM: Visual explanations from deep networks via gradient-based localization,” in Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 618–626. [15] A. Shorten and T. M. Khoshgoftaar, “A survey on image data augmentation for deep learning,” Journal of Big Data, vol. 6, no. 1, pp. 1–48, 2019. [16] M. Ahmad, S. Shabbir, M. Rashid, and A. Khalid, “Deep learning-based plant disease detection: A systematic review,” Plants, vol. 12, no. 3, pp. 1–24, 2023. [17] T. Hasan, A. R. Mohammed, and S. Khan, “Domain adaptation techniques for plant disease classification under real-field conditions,” Expert Systems with Applications, vol. 168, pp. 114-138, 2021. [18] P. Reyes, J. A. Escalante, and L. Villaseñor, “Drone-based plant disease detection using deep learning,” Remote Sensing, vol. 12, no. 6, pp. 1–20, 2020. [19] A. Chlingaryan, S. Sukkarieh, and B. Whelan, “Machine learning approaches for crop yield prediction and disease detection in agriculture,” Computers and Electronics in Agriculture, vol. 151, pp. 61–69, 2018.

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close