Integration of Concatenated Deep Learning Models with ResNet Backbone for Automated Corn Leaf Disease Identification

Achmad  imam sudianto; Sigit Susanto Putro; Eka Mala Sari; Ika Oktavia Suzanti; Aeri Rachmad; Wildan Surya Wijaya

doi:10.36456/3kct9e57

Authors

Achmad imam sudianto University of Trunojoyo Madura
Sigit Susanto Putro University of Trunojoyo Madura
Eka Mala Sari University of Trunojoyo Madura
Ika Oktavia Suzanti University of Trunojoyo Madura
Aeri Rachmad University of Trunojoyo Madura
Wildan Surya Wijaya University of PGRI Adibuana Surabaya

DOI:

https://doi.org/10.36456/3kct9e57

Keywords:

Digital Image Processing, Corn Leaf, Machine Learning, CNN

Abstract

Corn is one of Indonesia's food commodities, which is an alternative food that supports food diversification in Indonesia. However, leaf infections in corn plants often cause significant yield losses and threaten food security. Early detection of this disease is very important, especially for small farmers, because conventional diagnostic methods that rely on agronomists are expensive and time-consuming. Recent advances in Agricultural Artificial Intelligence (AI) and image processing have facilitated automatic plant disease recognition through Convolutional Neural Networks (CNN), with ResNet as the main backbone combined through concatenation with MobileNetV3, DenseNet161, and GoogleNet. The dataset consists of 4,000 images divided into 2,560 training data, 640 validation data, and 800 test data, with image sizes adjusted to 224×224 pixels. The dataset consists of 4,000 images distributed across four categories: gray leaf spot, common rust, northern leaf blight, and healthy leaf. The testing was conducted using three different optimizers, namely Adam, RMSprop, and SGD, with a learning rate of 0.01. The experimental results showed that the SGD optimizer provided the best performance with a loss value of 0.2275, accuracy of 0.9513, precision of 0.9536, recall of 0.9513, and F1-score of 0.9512. These findings confirm that the combination of ResNet, MobileNetV3, DenseNet161, and GoogleNet architectures with the SGD optimizer can significantly improve the accuracy of corn leaf disease detection, making it a potential application for automatic detection systems in support of smart farming practices.

References

O. Erenstein, M. Jaleta, K. Sonder, K. Mottaleb, and B. M. Prasanna, “Global maize production, consumption and trade: trends and R&D implications,” Food Security, vol. 14, no. 14, May 2022, doi: https://doi.org/10.1007/s12571-022-01288-7.

S. Amaruzaman, D. K. Bardsley, and R. Stringer, “Analysing agricultural policy outcomes in the uplands of Indonesia: A multi‐dimensional sustainability assessment,” Sustainable Development, vol. 31, no. 1, pp. 1937–1950, Jan. 2023, doi: https://doi.org/10.1002/sd.2494.

Y. Jiao, H.-D. Chen, H. Han, and Y. Chang, “Development and Utilization of Corn Processing by-Products: A Review,” Foods, vol. 11, no. 22, p. 3709, Nov. 2022, doi: https://doi.org/10.3390/foods11223709.

D. L. Nsibo, I. Barnes, and D. K. Berger, “Recent advances in the population biology and management of maize foliar fungal pathogens Exserohilum turcicum, Cercospora zeina and Bipolaris maydis in Africa,” Frontiers in Plant Science, vol. 15, Aug. 2024, doi: https://doi.org/10.3389/fpls.2024.1404483.

F. Mayo, C. Maina, M. Mgala, and N. Mduma, “Deep learning models for the early detection of maize streak virus and maize lethal necrosis diseases in Tanzania,” Frontiers in Artificial Intelligence, vol. 7, Aug. 2024, doi: https://doi.org/10.3389/frai.2024.1384709.

T. Zhu et al., “A Deep Learning Model for Accurate Maize Disease Detection Based on State-Space Attention and Feature Fusion,” Plants, vol. 13, no. 22, p. 3151, Nov. 2024, doi: https://doi.org/10.3390/plants13223151.

Saleem, Potgieter, and Mahmood Arif, “Plant Disease Detection and Classification by Deep Learning,” Plants, vol. 8, no. 11, p. 468, Oct. 2019, doi: https://doi.org/10.3390/plants8110468.

Y. Lu, S. Yi, N. Zeng, Y. Liu, and Y. Zhang, “Identification of rice diseases using deep convolutional neural networks,” Neurocomputing, vol. 267, pp. 378–384, Dec. 2017, doi: https://doi.org/10.1016/j.neucom.2017.06.023.

K. Shaheed et al., “EfficientRMT-Net—An Efficient ResNet-50 and Vision Transformers Approach for Classifying Potato Plant Leaf Diseases,” Sensors, vol. 23, no. 23, pp. 9516–9516, Nov. 2023, doi: https://doi.org/10.3390/s23239516.

S. PAN et al., “Intelligent diagnosis of northern corn leaf blight with deep learning model,” Journal of Integrative Agriculture, vol. 21, no. 4, pp. 1094–1105, Apr. 2022, doi: https://doi.org/10.1016/s2095-3119(21)63707-3.

A. Howard et al., "Searching for MobileNetV3," 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), 2019, pp. 1314-1324, doi: https://doi.org/10.1109/ICCV.2019.00140. [12]

G. Huang, Z. Liu, G. Pleiss, L. Van Der Maaten, and K. Weinberger, “Convolutional Networks with Dense Connectivity,” IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1–1, 2019, doi: https://doi.org/10.1109/tpami.2019.2918284.

H. B. G and V. N, “An efficient image dahazing using Googlenet based convolution neural networks,” Multimedia Tools and Applications, May 2022, doi: https://doi.org/10.1007/s11042-022-13222-2.

D. Singh, N. Jain, P. Jain, P. Kayal, S. Kumawat, and N. Batra, “PlantDoc: A Dataset for Visual Plant Disease Detection,” Proceedings of the 7th ACM IKDD CoDS and 25th COMAD, pp. 249–253, Jan. 2020, doi: https://doi.org/10.1145/3371158.3371196.

J. Yao, S. N. Tran, S. Garg, and S. Sawyer, “Deep Learning for Plant Identification and Disease Classification from Leaf Images: Multi-prediction Approaches,” arXiv (Cornell University), Jan. 2023, doi: https://doi.org/10.48550/arxiv.2310.16273.

M. Shafiq and Z. Gu, “Deep Residual Learning for Image Recognition: A Survey,” Applied Sciences, vol. 12, no. 18, p. 8972, Sep. 2022, doi: https://doi.org/10.3390/app12188972.

M. Krichen, “Convolutional Neural Networks: A Survey,” Computers, vol. 12, no. 8, pp. 151–151, Jul. 2023, doi: https://doi.org/10.3390/computers12080151.

X. Zhao, L. Wang, Y. Zhang, X. Han, M. Deveci, and M. Parmar, “A review of convolutional neural networks in computer vision,” Artificial Intelligence Review, vol. 57, no. 4, Mar. 2024, doi: https://doi.org/10.1007/s10462-024-10721-6.

S. Cong and Y. Zhou, “A review of convolutional neural network architectures and their optimizations,” Artificial Intelligence Review, vol. 56, no. 3, Jun. 2022, doi: https://doi.org/10.1007/s10462-022-10213-5.

F. He, T. Liu, and D. Tao, “Why ResNet Works? Residuals Generalize,” IEEE Transactions on Neural Networks and Learning Systems, pp. 1–14, 2020, doi: https://doi.org/10.1109/tnnls.2020.2966319.

A. Kopaničáková and R. Krause, “Globally Convergent Multilevel Training of Deep Residual Networks,” SIAM Journal on Scientific Computing, vol. 45, no. 3, pp. S254–S280, Aug. 2022, doi: https://doi.org/10.1137/21m1434076.

W. Huang and H. Zhang, “Convergence analysis of deep residual networks,” Analysis and Applications, vol. 22, no. 02, pp. 351–382, Sep. 2023, doi: https://doi.org/10.1142/s021953052350029x.

W. Xu, Y.-L. Fu, and D. Zhu, “ResNet and its application to medical image processing: Research progress and challenges,” Computer Methods and Programs in Biomedicine, vol. 240, p. 107660, Oct. 2023, doi: https://doi.org/10.1016/j.cmpb.2023.107660.

Aeri Rachmad, Muhammad Fuad, and S. Rochman, “Convolutional Neural Network-Based Classification Model of Corn Leaf Disease,” Mathematical modelling of engineering problems, vol. 10, no. 2, pp. 530–536, Apr. 2023, doi: https://doi.org/10.18280/mmep.100220.

S. Rochman et al., “Classification of Salt Quality Based on the Content of Several Elements in the Salt Using Machine Learning,” Mathematical Modelling and Engineering Problems, vol. 11, no. 4, pp. 1005–1012, Apr. 2024, doi: https://doi.org/10.18280/mmep.110417.

S. Susanto Putro, F. Adiputra, E. Mala Sari Rochman, A. Rachmad, M. A. Syakur, and S. Bayu Seta, “Comparison of SAW and WP methods to determine the best agricultural land,” Communications in Mathematical Biology and Neuroscience, Jan. 2021, doi: https://doi.org/10.28919/cmbn/5820.

Aeri Rachmad, Fifin Ayu Mufarroha, S. Rochman, Muhammad Ali Syakur, Firdaus Solihin, and Yuli Panca Asmara, “The Impact of Convolutional Layer Selection in ResNet-50v2 Architecture on Corn Leaf Disease Classification,” Ingénierie des systèmes d information, vol. 30, no. 6, Jun. 2025, doi: https://doi.org/10.18280/isi.300609.