Post-Harvest Onion Disease Identification and Classification Using Transfer Learning
Keywords:
Convolutional Neural Networks (CNNs), Transfer Learning, VGG16, ResNet50, Inceptionv3, F1-score.Abstract
The identification and classification of diseases in onions after harvest is critical for maintaining quality and minimizing economic losses. Traditional methods for disease detection are labor-intensive, subjective, and prone to error. This study investigates the use of transfer learning to develop an automated system for identifying and classifying healthy and diseased onions using image analysis. This is achieved by creating a model using transfer learning technique with pre-trained Convolutional Neural Networks (CNNs) models such as VGG16, ResNet50, and InceptionV3. Fine-tuning and dense layers are added at the end of the pretraining models for accurate classification of onions. Performance is assessed using metrics including accuracy, precision, recall, and F1-score. The ResNet50 model, in particular, achieved the highest accuracy, with a classification rate of 95.6%, outperforming other tested architectures. This approach promises to streamline post-harvest disease management, reduce losses, and ensure higher quality produce reaches consumers.
Downloads
References
Debasish Swapnesh Kumar Nayak, Saumendra Pattnaik, “Challenges and Solution for Identification of Plant Disease Using Machine Learning & IoT”, International Journal of Computer and Communication Technology, July 2023.
R. Manavalan, “Automatic identification of diseases in grains crops through computational approaches: A review”, Computers-and-Electronics-in-Agriculture, Volume 128, November 2020.
S. Divya Meena, Katakam Ananth Yasodharan Kumar, Devendra Mandava, “Plant Diseases Detection Using Transfer Learning”, Proceedings of Fourth International Conference on Computer and Communication Technologies, March 2023.
Lili Li, Shujuan Zhang, And Bin Wang, “Plant Disease Detection and Classification by Deep Learning—A Review”, IEEE Access PP(99), April 2021.
Muhammad Shoaib, Tariq Hussain, Babar Shah, Ihsan Ullah, Sayyed Mudassar, Farman Ali, Sang Hyun Park” Deep learning based segmentation and classification of leaf images for detection of tomato plant disease”, Front. Plant Sci., Sec. Plant Bioinformatics, 07 October 2022
Aanis Ahmad, Dharmendra Saraswat, Aly El Gamal, “A survey on using deep learning techniques for plant disease diagnosis and recommendations for development of appropriate tools”, Smart Agricultural Technology, Volume 3, February 2023.
Kunal Tyagi, Saksham Vats, Vasudha Vashisht, “Implementing Inception v3, VGG-16 and VGG-19 Architectures of CNN for Medicinal Plant leaves Identification and Disease Detection”, Journal of Electrical Engineering, Vol 20, May 2024.
Sakshi Srivastava, Prince Kumar, Noor Mohd, Anuj Singh, Fateh Singh Gill, "A Novel Deep Learning Framework Approach for Sugarcane Disease Detection", SN Computer Science, Springer Nature Journal, March 2020.
Fereshteh Shahoveisi, Hamed Taheri Gorji, Seyedmojtaba Shahabi, Seyedali Hosseinirad, Samuel Markell & Fartash Vasefi, “Application of image processing and transfer learning for the detection of rust disease”, Scientific Reports, 2023.
Yousef Methkal Abd Algani, Orlando Juan Marquez Caro, Liz Maribel Robladillo Bravo, “Leaf disease identification and classification using optimized deep learning”, Measurement: Sensors, Volume 25, February 2023.
Rudresh Dwivedi; Somnath Dey; Chinmay Chakraborty; Sanju Tiwari "Grape Disease Detection Network Based on Multi-Task Learning and Attention Features”, IEEE Sensors Journal, Vol. 21, No. 16, August 15, 2021.
Rashidul Hasan Hridoy; Mosammat Rokeya Anwar Tuli, "A Deep Ensemble Approach for Recognition of Papaya Diseases using EfficientNet Models”, International Conference on Electrical Engineering and Information Communication Technology (ICEEICT), 2021.
Andrew J, Jennifer Eunice, Daniela Elena Popescu, M. Kalpana Chowdar, Jude Hemanth "Deep Learning-Based Leaf Disease Detection in Crops Using Images for Agricultural Applications”, Agronomy 2022, 12(10), 2395; https://doi.org/10.3390/agronomy12102395.
S. B. et al., “Machine learning model for emotion detection and recognition using an enhanced Convolutional Neural Network,” Journal of Integrated Science and Technology, vol. 12, no. 4. The ScienceIn Publishing, Feb. 08, 2024. doi: 10.62110/sciencein.jist.2024.v12.786.
H. V. Ramachandra et al., “Secured Wireless Network Based on a Novel Dual Integrated Neural Network Architecture,” Journal of Electrical and Computer Engineering, vol. 2023. Hindawi Limited, pp. 1–11, Sep. 28, 2023. doi: 10.1155/2023/9390660.
D. R. Ganesh and M. Chithambarathanu, “Analyzing and securing information, images of women in online portal using CNN algorithm,” AIP Conference Proceedings. AIP Publishing, 2023. doi: 10.1063/5.0175977.
M. Chithambarathanu and D. Ganesh, “Character Recognition Tamil Language in Printed Images using Convolutional Neural Network (CNN) analysis,” 2021 4th International Conference on Computing and Communications Technologies (ICCCT). IEEE, Dec. 16, 2021. doi: 10.1109/iccct53315.2021.9711893.
Downloads
Published
How to Cite
Issue
Section
License
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.
