Empowering Agricultural Insights: RiceLeafBD -- A Novel Dataset and Optimal Model Selection for Rice Leaf Disease Diagnosis through Transfer Learning Technique

TL;DR

This work addresses rice leaf disease detection in Bangladesh by introducing RiceLeafBD, a field-collected dataset of 1,555 RGB images across four classes (Leaf Blight, Tungro virus, Brown Spot, Healthy). It compares a lightweight CNN baseline with three transfer-learning models—InceptionNet-V2, MobileNet-V2, and EfficientNet-V2—trained on 128x128 images with 50 epochs, using augmentation and standard multiclass metrics. EfficientNet-V2 achieves the top accuracy of 91.5%, outperforming the other models and suggesting that real-field data with transfer learning can yield robust disease identification. The dataset and findings provide practical insights for deploying rice-disease screening in Bangladesh and similar agrarian contexts, while also outlining avenues for dataset expansion and Transformer-based future work.

Abstract

The number of people living in this agricultural nation of ours, which is surrounded by lush greenery, is growing on a daily basis. As a result of this, the level of arable land is decreasing, as well as residential houses and industrial factories. The food crisis is becoming the main threat for us in the upcoming days. Because on the one hand, the population is increasing, and on the other hand, the amount of food crop production is decreasing due to the attack of diseases. Rice is one of the most significant cultivated crops since it provides food for more than half of the world's population. Bangladesh is dependent on rice (Oryza sativa) as a vital crop for its agriculture, but it faces a significant problem as a result of the ongoing decline in rice yield brought on by common diseases. Early disease detection is the main difficulty in rice crop cultivation. In this paper, we proposed our own dataset, which was collected from the Bangladesh field, and also applied deep learning and transfer learning models for the evaluation of the datasets. We elaborately explain our dataset and also give direction for further research work to serve society using this dataset. We applied a light CNN model and pre-trained InceptionNet-V2, EfficientNet-V2, and MobileNet-V2 models, which achieved 91.5% performance for the EfficientNet-V2 model of this work. The results obtained assaulted other models and even exceeded approaches that are considered to be part of the state of the art. It has been demonstrated by this study that it is possible to precisely and effectively identify diseases that affect rice leaves using this unbiased datasets. After analysis of the performance of different models, the proposed datasets are significant for the society for research work to provide solutions for decreasing rice leaf disease.

Figures (16)

• Figure 1: Sample images of datasets. (Normal Leaf, Leaf Blight, Brown Spot Leaf, and Tungro virus Leaf are presented from left to right for the above image)
• Figure 2: Proposed architecture of the Methodology
• Figure 3: Architecture of the CNN
• Figure 4: Confusion matrix of all models
• Figure 5: Accuracy and loss curve of InceptionNet-V2 model