Implementation of Transfer Learning Based Ensemble Model using Image Processing for Detection of Potato and Bell Pepper Leaf Diseases
Keywords:
Transfer Learning, ResNet, MobileNet, Inception, Potato Blight, Pepper Bell, Ensemble Model, Dirichlet ensembling, Deep Stacking ApproachAbstract
Globally, plant diseases are responsible for significant annual yield losses estimated at 10% to 15%, equivalent to a staggering economic impact of 100-150 billion USD. This research paper undertakes the critical challenge of addressing crop diseases, which pose an imminent threat to global food security due to their potential to cause substantial reductions in agricultural yield and production.The proposed approach leverages the power of ensemble learning, specifically employing the Dirichlet distribution-based ensemble technique. By harnessing the benefits of Dirichlet ensembling, it aims to enhance the accuracy and robustness of disease detection in plants.To achieve this objective,it harnesses the potential of image processing and deep learning methodologies to enable precise and automated detection of plant diseases. This approach not only minimizes the need for manual intervention but also significantly reduces the time and expertise required for disease identification.The suggested approach introduces a deep neural network (DNN) framework, thoughtfully incorporating Residual Network (ResNet), MobileNet, and Inception models within the ensemble. This ensemble-based approach synergistically combines these models to improve disease detection accuracy and reliability.To train and validate proposed ensemble model, a comprehensive dataset comprising both healthy and diseased potato leaves is utilized. The primary aim is to effectively discriminate between two categories of infected potato leaves and the single category of healthy potato leaves. In this proposed model exhibits remarkable proficiency in identifying nuanced features, color variations, and disease types within the leaves, successfully distinguishing between potentially infected and healthy foliage. Remarkably, proposed model achieves an outstanding overall accuracy rate of 98.86%. This achievement underscores the efficacy of propsoed Dirichlet ensemble-based deep learning approach for accurate detection and classification of potato diseases, facilitated by efficient image processing techniques.This study stands as a promising milestone in the realm of automated systems dedicated to the early identification and mitigation of plant diseases. By doing so, it holds the potential to significantly enhance agricultural productivity and, in turn, bolster global food security. The incorporation of Dirichlet ensembling adds an invaluable dimension to the research, further improving the model's performance and robustness in combating crop diseases.
Downloads
References
Exploring challenges and developing solutions for food security across 113 countries. Global Food Security Index 2022.
https://impact.economist.com/sustainability/project/food-security-index/
P. Jha, D. Dembla, W. Dubey, "Comparative Analysis of Crop Diseases Detection Using Machine Learning Algorithm", IEEE 3rd International Conference on Artificial Intelligence and Smart Energy, 2023.
Trong-Yen Lee, I-An Lin, Jui-Yuan Yu, Jing-min Yang, and Yu-Chun Chang, “High Efficiency Disease Detection for Potato Leaf with convolutional neural network”, Springer SN Computer Science 2, 297, 2021.
Yu Oishi, Harshana Habaragamuwa, Yu Zhang, Ryo Sugiura, Kenji Asano, Kotaro Akai, Hiroyuki Shibata, Taketo Fujimoto, "Automated abnormal potato plant detection system using deep learning models and portable video cameras", International Journal of Applied Earth Observation and Geoinformation, Volume 104,2021.
S. Bangari, P. Rachana, N. Gupta, P. S. Sudi, and K. K. Baniya, "A Survey on Disease Detection of a Potato Leaf Using CNN," 2022 Second International Conference on Artificial Intelligence and Smart Energy (ICAIS), pp. 144-149, 2022.
P. Jha, D. Dembla, W. Dubey, "Crop Disease Detection and Classification Using Deep Learning-Based Classifier Algorithm", Emerging Trends in Expert Applications and Security. ICETEAS 2023, Lecture Notes in Networks and Systems, vol 682, pp. 227-237, 2023.
Rashid, Javed, Imran Khan, Ghulam Ali, Sultan H. Almotiri, Mohammed A. AlGhamdi, and Khalid Masood, "Multi-Level Deep Learning Model for Potato Leaf Disease Recognition", MDPI Journal of Electronics 10, no. 17: 2064, 2021.
Md. Ashiqur Rahaman Nishad, Meherabin Akter Mitu, Nusrat Jahan, "Predicting and Classifying Potato Leaf Disease using K-means Segmentation Techniques and Deep Learning Networks", Procedia Computer Science, Volume 212, Pages 220-229, 2022.
P. Jha, D. Dembla and W. Dubey, “Deep learning models for enhancing potato leaf disease prediction: Implementation of transfer learning based stacking ensemble model”, Multimed Tools Application , 2023.
Xiao, Yuelei, and Xing Xiao, "An Intrusion Detection System Based on a Simplified Residual Network", MDPI Journal of Information 10, no. 11: 356, 2019.
S. K. Moon et al., "Deep learning-based detection of bacterial spot disease in bell pepper leaves using hyperspectral images, " IEEE Access, vol. 9, pp. 31566-31576, 2021.
K. Jo et al., "Detection of bell pepper diseases using transfer learning with convolutional neural networks," IEEE Access, vol. 9, pp. 49623-49631, 2021.
Y. H. Lee et al., "Real-time detection of powdery mildew in bell pepper using deep learning," IEEE Access, vol. 8, pp. 107824-107834, 2020.
S. Devi et al., "A comparative study of deep learning architectures for detecting bell pepper diseases," in 2020 International Conference on Communication and Signal Processing (ICCSP), pp. 0383-0387, 2020.
Y. L. Wu et al., "Identification of bell pepper diseases using a machine learning approach based on color and texture features," IEEE Access, vol. 7, pp. 175923-175932, 2019.
S. S. Behera et al., "Disease detection in bell pepper using machine learning techniques," in 2019 2nd International Conference on Inventive Research in Computing Applications (ICIRCA), pp. 317-321, 2019.
A. G. Vargas et al., "Automatic detection and classification of bell pepper plant diseases using machine learning techniques," IEEE Access, vol. 6, pp. 24426-24438, 2018.
M. H. Yeum et al., "A machine learning approach for identifying bell pepper diseases using spectral reflectance," in 2018 7th International Conference on Agro-Geoinformatics (Agro-Geoinformatics), pp. 1-6, 2018.
H. Kim et al., "Detection and classification of bell pepper diseases using deep convolutional neural networks," in 2018 IEEE International Conference on Big Data and Smart Computing (BigComp), pp. 99-102, 2018.
T. D. Tran et al., "Identification of bell pepper diseases using machine learning and color-based image segmentation," in 2018 International Conference on Advanced Computing and Applications (ACOMP), pp. 1-6, 2018.
]M. A. Hussain et al., "A deep learning approach for detecting bacterial spot disease in bell pepper leaves using hyperspectral images," Sensors, vol. 18, no. 11, 3902, 2018.
R. K. Thakur et al., "Machine learning approach for detection of powdery mildew disease in bell pepper," in 2018 7th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO), pp. 1053-1057, 2018.
Y. H. Lee et al., "An efficient approach for identifying bell pepper diseases using deep learning techniques," in 2018 15th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), pp. 477-482, 2018.
A. Kumar et al., "Automatic detection of bell pepper plant diseases using machine learning and computer vision," in 2017 2nd International Conference on Telecommunication and Networks (TEL-NET), pp. 139-142, 2017.
Vyas, S., M.K.M., S.K.A. (2023). An Efficient Approach for Plant Leaf Species Identification Based on SVM and SMO and Performance Improvement. In: Kulkarni, A.J., Mirjalili, S., Udgata, S.K. (eds) Intelligent Systems and Applications. Lecture Notes in Electrical Engineering, vol 959. Springer, Singapore. https://doi.org/10.1007/978-981-19-6581-4_1
Vyas, S., M.K.M., S.K.A. (2023). "Design and analysis of new algorithm for plant leaf species identification using by SVM and SMO." In AIP Conference Proceedings, vol. 2782, no. 1. AIP Publishing, 2023.
S. K. A. "A.. Raj, V. Sharma, and V. Kumar.“Simulation and Analysis of Hand Gesture Recognition for Indian Sign Language Using CNN”." International Journal on Recent and Innovation Trends in Computing and Communication 10, no. 4 (2022): 10-14.
Rajput, B. S. .; Gangele, A. .; S. K. A..; Raj, A, Design Simulation and Analysis of Deep Convolutional Neural Network Based Complex Image Classification System. ijfrcsce 2022, 8, 86-91.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Pradeep Jha, Deepak Dembla, Widhi Dubey
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
