CNN-Based Transfer Learning Model for Early Detection of Diseases in Corn Plants

Rima Maulini; Dwirgo Sahlinal; Dian Meilantika; Dani Rofianto; Tri Pujiana

doi:10.22146/jnteti.v15i2.24171

Rima Maulini Informatics Management Study Program, Department of Information Technology, Politeknik Negeri Lampung, Bandar Lampung, Lampung 13535, Indonesia
Dwirgo Sahlinal Informatics Management Study Program, Department of Information Technology, Politeknik Negeri Lampung, Bandar Lampung, Lampung 13535, Indonesia
Dian Meilantika Informatics Management Study Program, Department of Information Technology, Politeknik Negeri Lampung, Bandar Lampung, Lampung 13535, Indonesia
Dani Rofianto Informatics Management Study Program, Department of Information Technology, Politeknik Negeri Lampung, Bandar Lampung, Lampung 13535, Indonesia
Tri Pujiana Food Crop Production Technology Study Program, Food Crop Cultivation Department, Politeknik Negeri Lampung, Bandar Lampung, Lampung 13535, Indonesia

DOI: https://doi.org/10.22146/jnteti.v15i2.24171

Keywords: Transfer Learning, CNN, VGG16, ResNet101, Corn Disease

Abstract

Corn (Zea mays L.) is one of Indonesia’s primary food commodities, playing a crucial role in food security and the agricultural industry. However, its productivity is often compromised due to foliar diseases such as leaf blight, gray leaf spot, and common rust, significantly reducing crop yield. Conventional methods for disease detection rely on visual observation, which can be subjective, limited by the availability of agricultural experts, and delayed in disease control. To address these challenges, this study proposed a transfer learning-based approach utilizing convolutional neural networks (CNN) for early detection of maize diseases through digital images. The research implemented two widely used CNN architectures, Visual Geometry Group1 6 (VGG16) and residual network 101 (ResNet101), which were initialized with pretrained weights from ImageNet and fine-tuned to classify four maize leaf categories. The dataset consisted of 4,188 images, with 80% allocated for training and 20% for validation. Experimental results demonstrated that ResNet101 achieved the highest validation accuracy of 93.78%, with a validation loss of 0.2521, while VGG16 achieved a validation accuracy of 89.36% and a validation loss of 0.8905. These findings underscore the superiority of ResNet101 in terms of stability and generalization, whereas VGG16 is more efficient in computational resources. This study highlights the potential of transfer learning to facilitate rapid, accurate, and cost-effective disease detection, providing an essential tool for innovative farming applications in Indonesia, where limited data availability is often a barrier to implementing advanced artificial intelligence (AI) solutions.

References

E.Y. Tarigan, Widihastuty, and A.F.A. Sayu, “Effectiveness of corn (Zea mays ssp L. var. Saccharata) seed harvesting speed using a mini combine harvester in corn seed production,” J. Agron. Tanam. Trop. (JUATIKA), vol. 7, no. 1, pp. 129–134, Jan. 2025, doi: 10.36378/juatika.v7i1.3991.

S.R. br Siregar, and M.S. Sari, “Identification of disease and pathogen attack levels on corn (Zea mays) in BPP Stabat,” Serambi J. Agric. Technol., vol. 3, no. 2, pp. 83–90, Dec. 2021, doi: 10.32672/sjat.v3i2.3407.

A.A. Nampira and S. Mariam, “AI-assisted early detection of crop disease using hyperspectral imaging and deep learning in smallholder farms,” J. Multidiscip. Sustain. Asean, vol. 2, no. 3, pp. 109–119, Jun. 2025, doi: 10.70177/ijmsa.v2i3.2305.

A. Subeesh and C.R. Mehta, “Automation and digitization of agriculture using artificial intelligence and internet of things,” Artif. Intell. Agric., vol. 5, pp. 278-291, Dec. 2021, doi: 10.1016/j.aiia.2021.11.004.

M. Ryan, G. Isakhanyan, and B. Tekinerdogan, “An interdisciplinary approach to artificial intelligence in agriculture,” NJAS, Impact Agric. Life Sci., vol. 95, no. 1, pp. 1–31, Jan. 2023, doi: 10.1080/27685241.2023.2168568.

A. Tzachor et al., “Responsible artificial intelligence in agriculture requires systemic understanding of risks and externalities,” Nat. Mach. Intell., vol. 4, no. 2, pp. 104–109, Feb. 2022, doi: 10.1038/s42256-022-00440-4.

T. Kattenborn, J. Leitloff, F. Schiefer, and S. Hinz, “Review on convolutional neural networks (CNN) in vegetation remote sensing,” ISPRS J. Photogramm. Remote Sens., vol. 173, pp. 24–49, Mar. 2021, doi: 10.1016/j.isprsjprs.2020.12.010.

R. Yamashita, M. Nishio, R.K.G. Do, and K. Togashi, “Convolutional neural networks: An overview and application in radiology,” Insights Imaging, vol. 9, pp. 611–629, Aug. 2018, doi: 10.1007/s13244-018-0639-9.

Purwono et al., “Understanding of convolutional neural network (CNN): A review,” Int. J. Robot. Control Syst., vol. 2, no. 4, pp. 739–748, Dec. 2022, doi: 10.31763/ijrcs.v2i4.888.

I.D. Mienye and T.G. Swart, “A comprehensive review of deep learning: Architectures, recent advances, and applications,” Information, vol. 15, no. 12, pp. 1–45, Dec. 2024, doi: 10.3390/info15120755.

R. Hu et al., “The identification of corn leaf diseases based on transfer learning and data augmentation,” in CSSE '20, Proc. 3rd Int. Conf. Comput. Sci. Softw. Eng., 2020, pp. 58–65, doi: 10.1145/3403746.3403905.

M. Fraiwan, E. Faouri, and N. Khasawneh, “Classification of corn diseases from leaf images using deep transfer learning,” Plants, vol. 11, no. 20, pp.1–14, Oct. 2022, doi: 10.3390/plants11202668.

M. Iman, H.R. Arabnia, and K. Rasheed, “A review of deep transfer learning and recent advancements,” Technologies, vol. 11, no. 2, pp. 1–14, Apr. 2023, doi: 10.3390/technologies11020040.

B.D. Mardiana, et al., “Herbal leaves classification based on leaf image using CNN architecture model VGG16,” J. RESTI (Rekayasa Sist. Teknol. Inf.), vol. 7, no. 1, pp. 20–26, Feb. 2023, doi: 10.29207/resti.v7i1.4550.

A. Alshehri and D. AlSaeed, “Breast cancer diagnosis in thermography using pre-trained VGG16 with deep attention mechanisms,” Symmetry, vol. 15, no. 3, pp. 1–18, Mar. 2023, doi: 10.3390/sym15030582.

W. Bakasa and S. Viriri, “VGG16 feature extractor with extreme gradient boost classifier for pancreas cancer prediction,” J. Imaging, vol. 9, no. 7, pp. 1–22, Jul. 2023, doi: 10.3390/jimaging9070138.

A.A. Pravitasari et al., “UNet-VGG16 with transfer learning for MRI-based brain tumor segmentation,” TELKOMNIKA (Telecommun. Comput. Electron. Control), vol. 18, no. 3, pp. 1310–1318, Jun. 2020, doi: 10.12928/TELKOMNIKA.v18i3.14753.

S. Altun, A. Alkan, and İ. Altun, “LSS-VGG16: Diagnosis of lumbar spinal stenosis with deep learning” Clin. Spine Surg., vol. 36, no. 5, pp.180–190, Jun. 2023, doi: 10.1097/bsd.0000000000001418.

R. Syofiani and S. Islami, “Pengaruh berbagai dosis kompos kirinyuh (Chromolaena odorata) terhadap sifat kimia tanah dan hasil tanaman jagung (Zea mays L.),” J. Agrium, vol. 18, no. 1, pp. 52–56, Mar. 2021, doi: 10.29103/agrium.v18i1.3842.

N. Baharuddin, “Dampak perubahan tarif impor negara extra ASEAN terhadap pasar jagung Indonesia,” Amkop Manag. Account. Rev. (AMAR), vol. 1, no. 2, pp. 73–78, Jul.-Dec. 2021, doi: 10.37531/amar.v1i2.135.

A.W. Salehi et al., “A study of CNN and transfer learning in medical imaging: advantages, challenges, future scope,” Sustainability, vol. 15, no. 7, pp. 1–28, Apr. 2023, doi: 10.3390/su15075930.

K. Zhao, Y. Zhou, and X. Chen, “Object detection: Training from scratch,” IEEE Access, vol. 8, pp. 157520–157529, Aug. 2020, doi: 10.1109/ACCESS.2020.3018131.

Z. Zhao et al., “A comparison review of transfer learning and self-supervised learning: Definitions, applications, advantages and limitations,” Expert Syst. Appl., vol. 242, pp. 1–38, May 2024, doi: 10.1016/j.eswa.2023.122807.

Y. Wang et al., “An improved modulation recognition algorithm based on fine-tuning and feature re-extraction,” Electronics, vol. 12, no. 9, pp. 1–29, May 2023, doi: 10.3390/electronics12092134.