Detecting disorders in crops at an initial phase is important for improved agricultural productivity. Different diseases like purple blotch in onions affect crop quality worldwide. Traditional approaches for identifying purple blotch require time, wide examination, and frequent farm observation. With technical improvements in recent years, agriculturalists have been able to discover optimal solutions  that have caused higher harvests. This article presents compact Convolutional Neural Network (CNN) architecture for onion disease (purple blotch) classification from crop images. This Onion Crop Disease Dataset (OCDD) contains 1000 images of healthy and infected crops. Four distinct architectures InceptionV3, Xception, EfficientNetB7, and DenseNet201 are compared. Subsequent trials for assessment are applied. DenseNet201 delivers 94.54% accuracy in comparison to other models.

deep learning, convolutional neural network, classification, purple blotch, onion disease detection, data augmentation.

Received: November 1, 2024; Revised: November 28, 2024; Accepted: January 3, 2025; Published: January 10, 2025

How to cite this article: Muhammad Ahmed Zaki, Sammer Zai, Usman Amjad, Urooba  Zaki and Sanam Narejo, Compact convolutional neural network architecture for onion disease classification using crop images, Advances and Applications in Discrete Mathematics 42(3) (2025), 253-271. https://doi.org/10.17654/0974165825017

This Open Access Article is Licensed under Creative Commons Attribution 4.0 International License

References:
[1] A. Verma and M. S. Sabri, Precision agriculture using internet of things: an overview, International Journal of Management, IT and Engineering 9(7) (2019), 298-303.
[2] M. Jhuria, A. Kumar and R. Borse, Image processing for smart farming: detection of disease and fruit grading, 2013 IEEE Second International Conference on Image Information Processing (ICIIP-2013), Shimla, 2013, pp. 521-526.
doi: 10.1109/ICIIP.2013.6707647.
[3] G. Messina, J. M. Peña, M. Vizzari and G. Modica, A comparison of UAV and satellites multispectral imagery in monitoring onion crop. An application in the ‘Cipolla Rossa di Tropea’(Italy), Remote Sens. 12(20) (2020), 3424.
[4] H. Tamiru Geneti, The response of onion (Allium cepa L.) to applied water levels under pot planting at Mehoni, Raya valley of Ethiopia, Hawassa University, 2020.
[5] L. Black, K. Conn, B. Gabor, J. Kao and J. Lutton, Onion Disease Guide, Seminis, 2012, p. 71.
[6] R. D. Praba, K. Kavitha, S. Abinaya, P. Abarna, K. S. Shri and S. N. Shivappriya, Automatic tealeaf disease detection using machine and deep learning method, 2nd Int. Conf. Adv. Electr. Electron. Commun. Comput. Autom. ICAECA 2023, no. Cv, 2023, pp. 1-5. doi: 10.1109/ICAECA56562.2023.10200312.
[7] T. Priyaradhikadevi, R. Mohan, T. Ragupathi, S. Prasanna, K. Madhan and R. Ananthi, Leaf disease detection using machine learning algorithm, Proc. 8th IEEE Int. Conf. Sci. Technol. Eng. Math. ICONSTEM 2023, 2023, pp. 1-5.
doi: 10.1109/ICONSTEM56934.2023.10142564.
[8] U. Vignesh and B. S. Chokkalingam, EnC-SVMWEL: ensemble approach using CNN and SVM weighted average ensemble learning for sugarcane leaf disease detection, 2nd Int. Conf. Sustain. Comput. Data Commun. Syst. ICSCDS 2023 - Proc., 2023, pp. 1663-1668. doi: 10.1109/ICSCDS56580.2023.10104818.
[9] K. Thilagavathi, M. M. Sharafath, S. Abimanyu and K. Naveen, Disease detection in orange fruit using machine learning techniques, 2nd Int. Conf. Adv. Electr. Electron. Commun. Comput. Autom. ICAECA 2023, 2023, pp. 1-6.
doi: 10.1109/ICAECA56562.2023.10200184.
[10] D. R. Hammou and M. Boubaker, Tomato plant disease detection and classification using convolutional neural network architectures technologies, Smart Innov. Syst. Technol. 237 (2022), 33-44.
doi: 10.1007/978-981-16-3637-0-3.
[11] L. Vijayalakshmi and M. Sornam, Tomato disease detection using convolutional neural network and fuzzy logic, Artificial Intelligence and Evolutionary Computations in Engineering Systems, Springer, 2022, pp. 367-374.
[12] N. Moitra, A. Singh and S. Das, Use of convolutional neural network (CNN) to detect plant disease, Computational Advancement in Communication, Circuits and Systems, Springer, 2022, pp. 43-51.
[13] M. A. Zaki, S. Narejo, M. Ahsan, S. Zai, M. R. Anjum and N. U. Din, Image-based onion disease (Purple Blotch) detection using deep convolutional neural network, Int. J. Adv. Comput. Sci. Appl. 12(5) (2021), 448-458.
[14] M. Chandraprabha and R. K. Dhanraj, Ensemble deep learning algorithm for forecasting of rice crop yield based on soil nutrition levels, EAI Endorsed Scal. Inf. Syst. 10(4) (2023), 1-11.
[15] T. A. Salih, A. J. Ali and M. N. Ahmed, Deep learning convolution neural network to detect and classify tomato plant leaf diseases, Open Access Library Journal 07(05) (2020), 1-12.