An Enhancement of CNN Algorithm for Rice Leaf Disease Image Classification in Mobile Applications

作     者：Rodrigo, Kayne Uriel K. Marcial, Jerriane Hillary Heart S. Brillo, Samuel C. Mata, Khatalyn E. Morano, Jonathan C. 

作者机构：Computer Science Department College of Information Systems and Technology Management University of the City of Manila Manila Philippines Faculty in Biology Biology Department College of Science University of the City of Manila Manila Philippines Faculty in Computer Science Computer Science Department College of Information Systems and Technology Management University of the City of Manila Manila Philippines 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2024年

核心收录：

主　　题：Convolutional neural networks 

摘      要：This study focuses on enhancing rice leaf disease image classification algorithms, which have traditionally relied on convolutional neural network (CNN) models. We employed transfer learning with MobileViTV2_050 using ImageNet-1k weights—a lightweight model that integrates CNN’s local feature extraction with Vision Transformers’ global context learning through a separable self-attention mechanism. Our approach resulted in a significant 15.66% improvement in classification accuracy for MobileViTV2_050-A, our first enhanced model trained on the baseline dataset, achieving 93.14%. Furthermore, MobileViTV2_050-B, our second enhanced model trained on a broader rice leaf dataset, demonstrated a 22.12% improvement, reaching 99.6% test accuracy. Additionally, MobileViTV2-A attained an F1-score of 93% across four rice labels and a Receiver Operating Characteristic (ROC) curve ranging from 87% to 97%. In terms of resource consumption, our enhanced models reduced the total parameters of the baseline CNN model up to 92.50%, from 14 million to 1.1 million. These results indicate that MobileViTV2_050 not only improves computational efficiency through its separable self-attention mechanism but also enhances global context learning. Consequently, it offers a lightweight and robust solution suitable for mobile deployment, advancing the interpretability and practicality of models in precision agriculture. © 2024, CC BY.