A novel deep learning framework for identifying soybean salt stress levels using RGB leaf images

Abstract

Soybean is a crucial global oilseed crop and a vital source of plant protein. As one of the world's largest consumers of soybeans, China heavily relies on soybean imports, making increased soybean yields an effective way to address the shortage of soybean resources. As soil salinization becoming increasingly severe, salt stress has become a major factor affecting soybean yield and quality in China. This paper proposes a deep learning framework for identifying salt stress levels in soybean seedlings using RGB images of their leaves. In this framework, a Convolutional Neural Network combined with a Convolutional Block Attention Module is used to extract image features; a dimensionality reduction method is employed to remove redundancy from the extracted features; and a machine learning classifier is used to classify the reduced features. Experimental results demonstrate that this framework can accurately identify salt stress levels from soybean leaf images while overcoming the overfitting problem associated with small datasets. Compared to existing traditional deep learning models, transfer learning models, and other frameworks, the proposed framework offers better classification performance and generalization ability.

Plant phenotyping relevance

RGB葉画像からダイズ幼苗の塩ストレス状態を推定する深層学習フレームワークの開発・比較が中心であり、植物状態の画像ベースフェノタイピング手法に該当する。

Code and data availability

公開状態または取得可能な本文経路を確認できませんでした。

No evidence-backed public reproduction asset is currently recorded.