Classification of coffee leaf nutrient deficiencies using hybrid feature aggregation with hierarchical localized attention and MobileNet.

Abstract

Objectives Nutritional deficiency in coffee is a major problem that compromises plant health, crop yield, and bean quality, directly threatening the economies of coffee-dependent regions. Traditional detection methods are primarily manual, time-consuming, and relied upon expert availability. Methods This study introduces a novel Deep Learning (DL)-based dual-track architecture designed for the efficient classification of nutritional deficiencies in coffee leaf. The first track utilizes a MobileNetV3 backbone integrated with a Multi-Convolutional Shape-Aware Kernel (MCSK) block to capture spatially adaptive features from leaf textures and vein patterns. The second track employs a Hierarchical Shuffled Group Attention Network (HSGAN), utilizing Efficient Channel Attention (ECA) and Local Group Attention (LGA) modules to balance fine-grained local variations with broad spatial dependencies. Finally, a Multidimensional Collaborative Attention (MCA) mechanism is applied to the fused features to enhance cross-channel interactions and feature extraction. Results The proposed model was evaluated using the CoLeaf dataset, where it achieved an accuracy score of 96.04%. This performance demonstrates an improvement over existing research and current state-of-the-art models, highlighting the architecture's ability to identify complex nutrient-related patterns in coffee leaves. Conclusion The performance of the proposed DL approach offer a solution for the automated monitoring of coffee plants. By providing a reliable alternative to manual inspection, this method presents the potential to help coffee production and support the agricultural regions worldwide.

Plant phenotyping relevance

コーヒー葉の栄養欠乏という植物状態を画像から分類する深層学習手法を開発・評価しており、表現型取得・推定が研究の中心であるため。

Code and data availability

The paper's primary phenotyping asset is the CoLeaf coffee leaf nutrient-deficiency image dataset, which the authors state is publicly available via a Mendeley Data URL matching an allowed URL. No author analysis code or trained model checkpoints are disclosed.