Hybrid ResNet50-PCA based deep transfer learning approach for classification of tomato leaf diseases
Paper Details
Hybrid ResNet50-PCA based deep transfer learning approach for classification of tomato leaf diseases
Abstract
Tomato is one of the world’s most indispensable and consumable vegetable items. In the Indian market, it has high commercial value, and it is produced in huge quantities. The crop sensitivity and climatic conditions have made diseases familiar in the tomato crop during all the stages of its growth. It is a difficult task to monitor plant diseases manually due to its complex nature and time-consuming process. Artificial intelligence (AI) based computational models can detect leaf diseases in their early stages. In this article, ResNet50 a deep transfer learning based Convolutional Neural Network (CNN) amalgamated with Principal component analysis (PCA) to classify tomato leaf diseases effectively. Subset of publicly available ‘Plant Village’ dataset is used in this study. The architecture has attained the highest accuracy of 98.18% for identifying tomato leaf diseases. The experimental results show that the computational model effectively identifies tomato leaf disease and could be generalized to other plant diseases.
Adhikari S, Shrestha B, Baiju B, Kumar S. 2018. Tomato plant diseases detection system using image processing. In Proceedings of the 1st KEC Conference on Engineering and Technology 1(2), 81-86, Laliitpur, Nepal, 27 September.
Agarwal M, Singh A, Arjaria S, Sinha A, Gupta S. 2019 ToLeD: Tomato Leaf Disease Detection using Convolution Neural Network, In the proceedings of International Conference on Computational Intelligence and Data Science (ICCIDS 2019), Procedia Computer Science 167(2020), 293-301.
Bania KR. 2023. Ensemble of deep transfer learning models for real-time automatic detection of face mask, Multimedia Tools and Applications 1-23, https://doi.org/10.1007/s11042-023-14408-y.
Basavaiah J, Anthony AA. 2020. Tomato Leaf Disease Classification using Multiple Feature Extraction Techniques. Wirel. Pers. Commun 115(3), 633-651.
Hasan M, Tanawala B, Patel KJ. 2019. Deep learning precision farming: Tomato leaf disease detection by transfer learning. In Proceeding of the 2nd International Conference on Advanced Computing and Software Engineering (ICACSE), Sultanpur, India, 8-9 February.
Sabrol H, Satish K. 2016. Tomato plant disease classification in digital images using classification tree. In Proceedings ofthe International Conference on Communication and Signal Processing (ICCSP), 1242-1246, Melmaruvathur, India, 6-8 April.
Salih TA, Ali A, Ahmed M. 2020. Deep Learning Convolution Neural Network to Detect and Classify Tomato Plant Leaf Diseases. Open Access Library Journal 7(12), 1-12.
Schreinemachers P, Simmons EB, Wopereis MC. 2018. Tapping the economic and nutritional power of vegetables. Glob. Food Secur 16(1), 36-45.
Sharma R, Panigrahi A, Garanayak M. 2022. Tomato Leaf Disease Detection Using Machine Learning, ACI’22: Workshop on Advances in Computation Intelligence, its Concepts & Applications at ISIC 2022, May 17-19, Savannah, United States 294-299. https:// www.kaggle.com /kaustubhb999/tomatoleaf.
Stilwell M. 2023 The Global Tomato Online News Processing in 2018. Available online: https:// www. tomatonews.com.
Suryanarayana G, Chandran K, Khalaf OI, Alotaibi Y, Alsufyani A, Alghamdi SA. 2021. Accurate Magnetic Resonance Image Super-Resolution Using Deep Networks and Gaussian Filtering in the Stationary Wavelet Domain. IEEE Access 9, 71406-71417.
Weiss K. 2016. A survey of transfer learning, Journal of Big data 3(9), 1-40.
Wu Y, Xu L, Goodman ED. 2021. Tomato Leaf Disease Identification and Detection Based on Deep Convolutional Neural Network. Intelligent. Automatic Soft Computing 28, 561-576.
Rubul Kumar Bania, Sumit Dey, Nilutpal Buragohain, 2023. Hybrid ResNet50-PCA based deep transfer learning approach for classification of tomato leaf diseases. J. Biodiv. Environ. Sci., 22(4), 42-48.
Copyright © 2023 by the Authors. This article is an open access article and distributed under the terms and conditions of the Creative Commons Attribution 4.0 (CC BY 4.0) license.