Wheat leaf disease classification using modified ResNet50 convolutional neural network model

• Published in: Multimedia tools and applications 2024-01, Vol.83 (23), p.62875-62893
• Main Authors: Usha Ruby, A., George Chellin Chandran, J., Chaithanya, B. N., Swasthika Jain, T. J., Patil, Renuka
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Computer Communication Networks; Computer Science; Data Structures and Information Theory; Datasets; Deep learning; Disease; Feature extraction; Generative adversarial networks; Image classification; Machine learning; Medical imaging; Missing data; Multimedia Information Systems; Neural networks; Plant diseases; Special Purpose and Application-Based Systems; Wheat
• ISSN: 1573-7721; 1380-7501; 1573-7721
• DOI: 10.1007/s11042-023-18049-z

Wheat leaf disease prevention and treatment requires an accurate and rapid classification of wheat leaf diseases and their extent. Using healthy wheat, leaf rust, crown, root rot, and wheat loose smut as research objects, this study proposes a deep learning-based technique for classifying wheat leaf diseases. A collaborative generative adversarial network is used as an image imputation in the proposed methodology, allowing a generator and discriminator network to properly estimate the missing data in the dataset using the residual method. It is used to improve feature extraction in wheat leaf images. The major contribution of this study is to use a pre-trained deep learning convolutional neural network architecture as a foundation to improve and construct an automated tool for wheat leaf disease image categorization. To classify wheat leaf diseases, a modification to the Residual Network with 50 layers (ResNet50) is being suggested. The ′Conv′, ′Batch Normaliz′, and ′Activation Leaky Relu′ layers were added as part of this modification. These layers are inserted into the ResNet50 architecture for accurate feature extraction and discrimination. Extensive tests are carried out to evaluate the proposed model's performance on photos from a large wheat disease classification dataset. The suggested approach outperforms ResNet50, InceptionV3, and DenseNet, according to the experimental findings. The suggested method achieves the greatest identification accuracy of 98.44%. These discoveries might aid in the accurate detection and categorization of wheat leaf diseases.