Related Experiment Videos
Multi-FusNet-convolutional neural network with improved Huber loss function for plant leaf disease detection and
B S Shruthi1,2, M S Narasimha Murthy2, Eman Abdullah Aldakheel3
1Department of Computer Science and Engineering, Malnad College of Engineering, Hassan, India, Belagavi, India.
Frontiers in Plant Science
|May 20, 2026
Summary
This study introduces a novel Multi-FusNet-convolutional neural network (CNN) for accurate plant leaf disease detection and classification. The developed model achieves high performance, significantly aiding agricultural disease management.
Area of Science:
- Agricultural Science
- Computer Science
- Machine Learning
Background:
- Plant disease detection and classification are critical for agriculture, enabling farmers to prevent disease spread.
- Overlapping disease characteristics present significant challenges in accurate identification.
Purpose of the Study:
- To develop an advanced deep learning model for multi-class plant leaf disease classification.
- To enhance the accuracy and generalization capability of plant disease detection systems.
Main Methods:
- A Multi-FusNet-convolutional neural network (CNN) integrating a multipath residual network (Multi-RG) with cross-filtering and pixel shuffling fusion was developed.
- An improved Huber loss function was incorporated to enhance outlier handling and model generalization.
Main Results:
- The Multi-FusNet-CNN achieved exceptional performance with 99.95% accuracy, 99.13% F1-score, 99.87% recall, 99.27% precision, and 99.93% specificity.
- The model outperformed existing conventional techniques in plant leaf disease classification.
Conclusions:
- The proposed Multi-FusNet-CNN model demonstrates improved generalization capabilities for plant leaf disease detection and classification.
- This advancement offers a robust solution for early and accurate identification of plant diseases in agriculture.
