Abstract
Rice is a widely used grain product all over the world, and obtaining high-quality rice products is crucial. However, the quantity and quality of rice products can be reduced due to rice diseases. Detecting these diseases is challenging, as rice is cultivated in large, wet areas. Therefore, computer-aided systems for identifying rice diseases are of great significance. In this study, we propose a novel approach for detecting diseases in rice plants. Our approach employs three different convolutional neural networks (CNNs), namely Efficientb0, Shufflenet, and Resnet101. We extract feature maps from these networks, combine them, and then classify them using support vector machine (SVM). Additionally, seven different CNN architectures are employed to compare results. Our proposed approach achieves the highest accuracy value of 98%, demonstrating its potential for accurately classifying diseases in rice plants.
This is a preview of subscription content, log in via an institution to check access.
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Availability of data and materials
Thanks to the dataset owners for sharing the dataset used in this study [15].
References
Krishnamoorthy, N., et al.: Rice leaf diseases prediction using deep neural networks with transfer learning. Environ. Res. 198, 111275 (2021)
Ghosal, S., K. Sarkar.: Rice leaf diseases classification using CNN with transfer learning. In: 2020 IEEE Calcutta Conference (CALCON). IEEE. (2020)
Ökten, İ, Yüzgeç, U.: Evrişimli Sinir Ağı ile Çeltik Bitkisi Hastalığının Tespiti. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi. 11(1), 203–217 (2022)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural. Inf. Process. Syst. 25, 1097–1105 (2012)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition. (2016)
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Rabinovich, A.: Going deeper with convolutions. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition. (2015)
Zhang, X., Zhou, X., Lin, M., Sun, J.: Shufflenet: An extremely efficient convolutional neural network for mobile devices. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 6848–6856. (2018)
Tan, M. and Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. Paper presented at the International Conference on Machine Learning. (2019)
Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767. (2018)
Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Adam, H.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861. (2017)
Altman, E.I., Marco, G., Varetto, F.: Corporate distress diagnosis: comparisons using linear discriminant analysis and neural networks (the Italian experience). J. Bank. Finance 18(3), 505–529 (1994)
Jiang, F., et al.: Image recognition of four rice leaf diseases based on deep learning and support vector machine. Comput. Electron. Agric. 179, 105824 (2020)
Pothen, M.E., M.L. Pai.: Detection of rice leaf diseases using image processing. In 2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC). IEEE (2020)
Lu, Y., et al.: Identification of rice diseases using deep convolutional neural networks. Neurocomputing 267, 378–384 (2017)
“Rice Leafs Disease Dataset | Kaggle.” Available from: https://www.kaggle.com/datasets/dedeikhsandwisaputra/rice-leafs-disease-dataset.
Eroglu, Y., Yildirim, K., Çinar, A., Yildirim, M.: Diagnosis and grading of vesicoureteral reflux on voiding cystourethrography images in children using a deep hybrid model. Comput. Methods Programs Biomed. 210, 106369 (2021)
Funding
We received no funding to support our study.
Author information
Authors and Affiliations
Contributions
The contributions of the authors are equal.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there is no conflict of interest in the study.
Ethical approval
Not required.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Yucel, N., Yildirim, M. Automated deep feature fusion based approach for the classification of multiclass rice diseases. Iran J Comput Sci 7, 131–138 (2024). https://doi.org/10.1007/s42044-023-00152-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42044-023-00152-x