MobileNetV2-Based Approaches for Plant Disease Detection: A Systematic Review

DOI

10.2991/978-94-6239-713-2_30How to use a DOI?

Keywords

MobileNetV2; crop disease detection; Plant Village dataset; convolutional neural network (CNN)

Abstract

Control and early intervention with crop diseases is a serious issue in contemporary agriculture, which directly affects food security in the world and livelihoods of farmers. This paper will encapsulate developments in the field of detecting plant diseases and will show that MobileNetV2 is decisively better than ResNet50 (99.41) and InceptionResNetV2 (99.09) when using the same datasets [5], also being much faster, so it will be the most desirable framework to implement these applications that rely on a small footprint and are of top quality. The review confirms MobileNetV2 has a maximum accuracy of 100 per cent and is 6.1 times faster in inference than EfficientNetV2S in [10] and ensemble models that use it and ResNet50 support 99.91 percent accuracy [11], making it a highly suitable model to deploy in resource-constrained hardware in real-time mode. The evaluation combines popular improvement methods, such as the ubiquitous application of transfer learning and data augmentation, and specialized ones, such as ensemble and specialized hybrid models. But the paper also lists two enduring obstacles to a general adoption of the technology, namely the domain gap between the laboratory-trained models and the field conditions and the Black Box Problem, which restricts the trust of farmers. We conclude the paper by suggesting a future-ready system with MobileNetV2 architecture and Explainable AI (XAI) and IoT sensor data, which has been the required next step to achieve the sustainable, intelligent, and data-driven future of crop health management.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Vijaya Krishna Tela
AU  - Priyanka Gupta
AU  - Pirla Khagesh
AU  - P. Sarvesh
AU  - Chinchilapu Adharsh
AU  - Guzzarlapudi Prince Nihal
PY  - 2026
DA  - 2026/06/25
TI  - MobileNetV2-Based Approaches for Plant Disease Detection: A Systematic Review
BT  - Proceedings of the International Conference on Advances in Computing Technology and Artificial Intelligence (COMPUTATIA 2026)
PB  - Atlantis Press
SP  - 394
EP  - 405
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-713-2_30
DO  - 10.2991/978-94-6239-713-2_30
ID  - Tela2026
ER  -