A comparative study of baseline convolutional neural network and ResNet50 for image-based tomato leaf disease classification

Abstract

Image-based techniques are widely used in plant disease classification to support agricultural productivity and facilitate early detection. This study presents a comparative analysis between a baseline convolutional neural network (CNN) and a ResNet50-based transfer learning model for tomato leaf disease classification. A publicly available dataset containing five categories—tomato bacterial spot, tomato late blight, tomato septoria leaf spot, tomato yellow leaf curl virus, and healthy leaves—was used in the experiments. Model performance was evaluated using several standard classification metrics, with emphasis on overall accuracy. The baseline CNN achieved an accuracy of 97.0%, whereas the ResNet50 model reached 99.6%. The results demonstrate that the ResNet50 model produces more stable and reliable predictions, particularly when distinguishing between visually similar disease classes. These findings confirm that transfer learning can effectively improve classification performance in plant disease recognition tasks.

Plant phenotyping relevance

トマト葉の病徴を画像から分類するCNN/ResNet50手法を比較評価しており、植物病害状態の取得・推定が研究の中心である。

Code and data availability

The paper uses the publicly available PlantVillage tomato leaf dataset, but this is a pre-existing community benchmark (cited prior work), not a paper-specific deposit. No author code, trained models, or paper-specific data repository is provided; the data availability statement only points generically to PlantVillage.

No evidence-backed public reproduction asset is currently recorded.