A Multi-Scale Feature Extraction and Fusion Deep Learning Method for Classification of Wheat Diseases

TL;DR

This paper presents a deep learning ensemble approach using multi-scale feature extraction and fusion techniques to classify wheat diseases with high accuracy, improving upon existing methods.

Contribution

It introduces a novel combination of multi-scale feature extraction, advanced neural networks, and ensemble classifiers for wheat disease classification.

Findings

Achieved 99.75% classification accuracy.

Xception model outperformed other neural networks.

Ensemble methods improved overall accuracy.

Abstract

Wheat is an important source of dietary fiber and protein that is negatively impacted by a number of risks to its growth. The difficulty of identifying and classifying wheat diseases is discussed with an emphasis on wheat loose smut, leaf rust, and crown and root rot. Addressing conditions like crown and root rot, this study introduces an innovative approach that integrates multi-scale feature extraction with advanced image segmentation techniques to enhance classification accuracy. The proposed method uses neural network models Xception, Inception V3, and ResNet 50 to train on a large wheat disease classification dataset 2020 in conjunction with an ensemble of machine vision classifiers, including voting and stacking. The study shows that the suggested methodology has a superior accuracy of 99.75% in the classification of wheat diseases when compared to current state-of-the-art approaches. A deep learning ensemble model Xception showed the highest accuracy.