RTCB: an integrated deep learning model for garlic leaf disease identification.

Abstract

Problem Garlic is a common ingredient that not only enhances the flavor of dishes but also has various beneficial effects and functions for humans. However, its leaf diseases and pests have a serious impact on the growth and yield. Traditional plant leaf disease detection methods have shortcomings, such as high time consumption and low recognition accuracy. Methodology As a result, we present a deep learning approach based on an upgraded ResNet18, triplet, convolutional block (RTCB) attention mechanism for recognizing garlic leaf diseases. First, we replace the convolutional layers in the residual block with partial convolutions based on the classic ResNet18 architecture to improve computational efficiency. Then, we introduce triplet attention after the first convolutional layer to enhance the model's ability to focus on key features. Finally, we add a convolutional block attention mechanism after each residual layer to improve the model's feature perception. Results The experimental results demonstrate that the proposed model achieves a classification accuracy of 98.90%, which is superior to outstanding deep learning models such as Efficient-v2-B0, MobileOne-S0, OverLoCK-S, EfficientFormer, and MobileMamba. The proposed RTCB has a faster computation speed, higher recognition precision, and stronger generalization ability. Contribution The proposed approach provides a scalable technical reference for the engineering application of automatic disease monitoring and control in intelligent agriculture. The current strategy is conducive to the deployment of edge computing equipment and has extensive significance and application potential in plant leaf disease detection.

Plant phenotyping relevance

ニンニク葉の病害状態を画像から識別する深層学習モデルの開発・比較評価が中心であり、植物病害フェノタイピング手法に該当する。

Code and data availability

The supplied blocks describe a privately collected garlic leaf image dataset (9,076 images from garlic planting bases in Henan Province) and a custom RTCB model, but contain no public dataset deposit, no author code/model release, and no data availability statement text with a public URL. No paper-specific public asset

No evidence-backed public reproduction asset is currently recorded.