Agricultural Engineering

Comparison of Different Deep Learning Architectures for Corn Seed Classification

Document Type : Applicable

Authors

Samaneh Akbari 1
Omidali Akbarpour 2
Amin Taheri-Garavand 3

1 Ph.D. Candidate, Department of Plant Production and Genetics Engineering, Faculty of Agriculture, Lorestan University

2 Assistant Professor, Department of Plant Production and Genetics Engineering, Faculty of Agriculture, Lorestan University

3 Associate Professor, Mechanical Engineering of Biosystems Department, Lorestan University

https://doi.org/10.22055/agen.2026.52047.1804
Abstract
Introduction: Corn (Zea mays L.) is a strategic crop for global food security, feed, and biofuel. Genetic purity of hybrid seeds is vital for high yield and stress resistance. However, different corn varieties often look very similar. Subtle differences in color, texture, shape, and size make traditional identification difficult. Manual inspection is time-consuming, subjective, error-prone, and not scalable. Thus, an automated, non-destructive, and accurate system is needed. Deep learning, especially CNNs, is a powerful tool for agricultural image recognition. Mobile-optimized networks like MobileNet and NASNetMobile offer a good balance between accuracy and efficiency. They are suitable for smartphones and embedded systems. This study compares six deep learning architectures for non-destructive identification of five Iranian corn seed varieties.

Materials and Methods: Six deep learning architectures were evaluated including base MobileNet, DenseNet121, MobileNetV2, MobileNetV3Small, MobileNetV3Large, and NASNetMobile. All models were pre-trained on ImageNet and fine-tuned for corn seed classification. A total of 9,374 high-resolution images of five corn seed classes (KSC201, KSC260, KSC400, KSC703, KSC705) were acquired under controlled conditions. The dataset was split into training (6114 images, 65.2%), validation (1875 images, 20%), and test (1385 images, 14.8%) sets. Models were trained using the Adam optimizer (learning rate 0.0001) for 50 epochs with categorical cross-entropy loss. Data augmentation (rotation, shift, zoom, flip) was applied to enhance generalization. Performance was evaluated using accuracy, precision, recall, specificity, F1-score, ROC curves, AUC, confusion matrices, and training time.

Results and Discussion: MobileNet achieved the best overall performance with 97.04% accuracy, 96.66% precision, 96.70% recall, 99.27% specificity, and 96.67% F1-score. DenseNet121 ranked second with 95.96% accuracy and 95.41% F1-score. MobileNetV3Small (95.02% accuracy, 94.20% F1-score) outperformed MobileNetV3Large (93.43% accuracy, 92.82% F1-score). MobileNetV2 achieved 93.14% accuracy and 92.71% F1-score, while NASNetMobile recorded the weakest performance with 87.08% accuracy and 86.22% F1-score. All models showed high specificity ranging from 96.77% to 99.27%. Class-wise analysis revealed that KSC260 was the most stable class with F1-scores of 98.01% for MobileNet, 98.15% for MobileNetV3Small, 98.13% for DenseNet121, and 96.9% for MobileNetV2. KSC703 also performed well with F1-scores of 98.42% for MobileNet and 98.27% for DenseNet121. In contrast, KSC705 was the most challenging class; MobileNetV2 showed extreme behavior on KSC705 with 99.24% recall but only 77.74% precision, resulting in a low 87.19% F1-score. Persistent misclassifications occurred between class pairs KSC201/KSC705 and KSC400/KSC705 across all models, indicating significant feature overlap. ROC curve analysis showed that MobileNet, DenseNet121, MobileNetV3Small, and MobileNetV3Large achieved an ideal AUC of 1.00, while MobileNetV2 and NASNetMobile recorded excellent AUC values of 0.99 and 0.98, respectively. Regarding computational efficiency, training time varied significantly: MobileNet required 108.32 minutes (highest), DenseNet121 required 104.66 minutes, while MobileNetV3Small required only 62.28 minutes, offering a 46-minute reduction compared to MobileNet while maintaining 95.02% accuracy. MobileNetV2 (60.77 min), MobileNetV3Large (63.96 min), and NASNetMobile (64.04 min) showed moderate efficiency. There is a clear trade-off between accuracy and computational efficiency: MobileNet provides maximum accuracy (97.04%) but requires the most training time (108.32 min), whereas MobileNetV3Small offers a balanced solution with 95.02% accuracy and 62.28 min training time. Therefore, for maximum absolute accuracy without computational constraints, MobileNet is the top choice; for a balanced trade-off between accuracy and efficiency, DenseNet121 is suitable; and for resource-constrained environments such as mobile devices, MobileNetV3Small is the best option.

Conclusion: This study demonstrates that mobile-optimized deep learning architectures, particularly base MobileNet and MobileNetV3Small, possess high potential for accurate, non-destructive, and efficient classification of corn seed varieties. These findings provide a practical reference for researchers and engineers in automated agricultural product classification, offering clear architecture selection guidelines based on specific application constraints.

Keywords

Confusion Matrix
Corn
Deep Learning
Image Processing
MobileNet
Subjects
  1. Akbarpour, O., Akbari, S., Fanourakis, D., and Taheri-Garavand, A. 2026. Deep learning-based seed variety classification: a case study in maize. BMC Plant Biology, 26, Article 105. https://doi.org/10.1186/s12870-025-07919-3
  2. Alkanan, M., and Gulzar, Y. 2024. Enhanced corn seed disease classification: leveraging MobileNetV with feature augmentation and transfer learning. Frontiers in Applied Mathematics and Statistics, 10: 24. https://doi.org/10.3389/fams.2023.1320177.
  3. Bora, M. B., Daimary, D., Amitab, K., and Kandar, D. 2020. Handwritten Character Recognition from Images using CNN-ECOC. Procedia Computer Science, 167: 2403–2409. https://doi.org/10.1016/j.procs.2020.03.293.
  4. Chen, J., Zhang, D., Suzauddola, M., Nanehkaran, Y. A., and Sun, Y. 2021. Identification of plant disease images via a squeeze-and-excitation MobileNet model and twice transfer learning. IET Image Processing, 15(5): 1115–1127. https://doi.org/10.1049/ipr2.12090.
  5. Chen, Y., Chen, X., Lin, J., Pan, R., Cao, T., Cai, J., Yu, D., Cernava, T., and Zhang, X. 2022. DFCANet: A Novel Lightweight Convolutional Neural Network Model for Corn Disease Identification. Agriculture, 12(12): 2047. https://doi.org/10.3390/agriculture12122047
  6. Cinar, A., and Yildirim, M. 2020. Detection of tumors on brain MRI images using the hybrid convolutional neural network architecture. Medical Hypotheses, 139: 109684. https://doi.org/10.1016/j.mehy.2020.109684.
  7. Erenstein, O., Jaleta, M., Sonder, K., Mottaleb, K., and Prasanna, B. M. 2022. Global maize production, consumption and trade: trends and R&D implications. Food Security, 14(5): 1295-1319. https://doi.org/10.1007/s12571-022-01288-7E
  8. Esteva, A., Chou, K., Yeung, S., Naik, N., Madani, A., Mottaghi, A., Liu, Y., Topol, E., Dean, J., and Socher, R. 2021. Deep learning-enabled medical computer vision. NPJ Digital Medicine, 4(1): 5. https://doi.org/10.1038/s41746-020-00376-2
  9. Feng, X., Zhang, H., Zhou, R., Qiao, L., Wei, D., Li, D. D., Zhang, Y. Y., and Zheng, G. Q. 2021. Variety Recognition Based on Deep Learning and Double-Sided Characteristics of Maize Kernel. Journal of System Simulation, 33: 2983–2991. https://doi.org/10.16182/j.issn1004731x.joss.21-FZ0771
  10. Gebeyehu, S., and Sintayehu Shibeshi, Z. 2024. Maize seed variety identification model using image processing and deep learning. Indonesian Journal of Electrical Engineering and Computer Science, 33: 990-998. https://doi.org/10.11591/ijeecs.v33.i2.pp990-998
  11. Gong, E. J., Bang, C. S., and Lee, J. J. 2024. Edge Artificial Intelligence Device in Real-Time Endoscopy for Classification of Gastric Neoplasms: Development and Validation Study. Biomimetics, 9: 783. https://doi.org/10.3390/biomimetics9120783
  12. He, K., Zhang, X., Ren, S., and Sun, J. 2016. Deep Residual Learning for Image Recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 770–778). Las Vegas, NV, USA. https://doi.org/10.1109/CVPR.2016.90
  13. Hu, J., Deng, X., Pan, Y., Wang, Y., and Jin, W. 2023. Temporal Encoded Deep Learning Radiomics Model for Preoperative Prediction of Microvascular Invasion in Hepatocellular Carcinoma. Journal of Medical and Biological Engineering, 43(5): 623–632. https://doi.org/10.1007/s40846-023-00829-5
  14. Jaithavil, D., Triamlumlerd, S., and Pracha, M. 2022. Paddy Seed Variety Classification Using Transfer Learning Based on Deep Learning. In Proceedings of the 2022 International Electrical Engineering Congress (iEECON) (pp. 1–4). Khon Kaen, Thailand. https://doi.org/10.1109/iEECON53204.2022.9741677
  15. Javid, A. M., Das, S., Skoglund, M., and Chatterjee, S. 2021. A ReLU Dense Layer to Improve the Performance of Neural Networks. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2810–2814. https://ieeexplore.ieee.org/document/9414269
  16. Jia, S., An, D., Liu, Z., Gu, J., Li, S., Zhang, X., Zhu, D., Guo, T., and Yan, Y. 2015. Variety identification method of coated maize seeds based on near-infrared spectroscopy and chemometrics. Journal of Cereal Science, 63: 21-26. https://doi.org/10.1016/j.jcs.2014.07.003
  17. Jiao, L., Liang, M., Chen, H., Yang, S., Liu, H., and Cao, X. 2017. Deep Fully Convolutional Network-Based Spatial Distribution Prediction for Hyperspectral Image Classification. IEEE Transactions on Geoscience and Remote Sensing, 55: 5585–5599. https://doi.org/10.1109/TGRS.2017.2710079
  18. Khaki, S., Pham, H., Han, Y., Kuhl, A., Kent, W., and Wang, L. 2021. DeepCorn: A semi-supervised deep learning method for high-throughput image-based corn kernel counting and yield estimation. Knowledge-Based Systems, 218: 1-27. https://doi.org/10.1016/j.knosys.2021.106874
  19. Khan, E., Rehman, M.Z.U., Ahmed, F., and Khan, M.A. 2021. Classification of Diseases in Citrus Fruits Using SqueezeNet. In Proceedings of the 2021 International Conference on Applied and Engineering Mathematics (ICAEM), London, UK, 7–9 July 2021 (pp. 67–72). https://doi.org/10.1109/ICAEM53552.2021.9547133
  20. Kim, P. H., Yoon, H. M., Kim, J. R., Hwang, J.-Y., Choi, J.-H., Hwang, J., Lee, J., Sung, J., Jung, K.-H., Bae, B., Jung, A. Y., Cho, Y. A., Shim, W. H., Bak, B., and Lee, J. S. 2023. Bone Age Assessment Using Artificial Intelligence in Korean Pediatric Population: A Comparison of Deep-Learning Models Trained With Healthy Chronological and Greulich-Pyle Ages as Labels. Korean Journal of Radiology, 24(11): 1151. https://doi.org/10.3348/kjr.2023.0092
  21. Korkmaz, A., Tenekeci, M. E., and Çodur, M. Y. 2025. Comparison of Deep Learning Models in Automatic Classification of Corn Seed Diseases Using Leaf Images. PeerJ Computer Science, 11: e2453. https://doi.org/10.7717/peerj-cs.2453
  22. Kumar, S., Lamichaney, A., Sripathy, K., Dinni, S., and Kamble, U. R. 2025. Modern molecular techniques to support hybrid seed industry in crop plants. In Hybrid Seed Production for Boosting Crop Yields: Applications, Challenges and Opportunities (pp. 535–557). Springer.
  23. Liu, X., Centeno, J., Alvarado, J., and Tan, L. 2022. One Dimensional Convolutional Neural Networks Using Sparse Wavelet Decomposition for Bearing Fault Diagnosis. IEEE Access, 10: 86998–87007. https://doi.org/10.1109/ACCESS.2022.3199381
  24. Maximilliano, W., and Rachmat, N. 2025. Comparative Analysis of MobileNetV3-Large and Small for Corn Leaf Disease Classification. Brilliance: Research of Artificial Intelligence, 5(1). https://doi.org/10.47709/brilliance.v5i1.6259
  25. Oka, I. G. R. L., Ariana, A. A. G. B., Peradhayana, W. S., Ginantra, N. L. W. S. R., and Sutarwiyasa, I. K. 2025. Performance Comparison of MobileNetV2 and NASNetMobile Architectures in Soybean Leaf Disease Classification. Indonesian Journal of Data and Science, 6(2). https://doi.org/10.56705/ijodas.v6i2.243
  26. Phung, V. H., and Rhee, E. J. 2019. A High-Accuracy Model Average Ensemble of Convolutional Neural Networks for Classification of Cloud Image Patches on Small Datasets. Applied Sciences, 9: 21. https://doi.org/10.3390/app9214500
  27. Sarvamangala, D. R., and Kulkarni, R. V. 2022. Convolutional neural networks in medical image understanding: a survey. Evolutionary Intelligence, 15(1): 1–22. https://doi.org/10.1007/s12065-020-00540-3.
  28. Setiawan, D. R., Prakasa, E., Al Riza, D. F., Sumarlan, S. H., and Aqil, M. 2025. Deep Learning Approach for the Morphological Differentiation of Corn Seed Types. Electronic Letters on Computer Vision and Image Analysis, 22(2): 70-80. https://doaj.org/article/18d907b5e02740c39a43c3a93be6bece
  29. Simonyan, K., and Zisserman, A. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In Proceedings of the 3rd International Conference on Learning Representations (ICLR) (pp. 1–14). San Diego, CA, USA. https://arxiv.org/abs/1409.1556
  30. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. 2016. Rethinking the Inception Architecture for Computer Vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 2818–2826). Las Vegas, NV, USA. https://doi.org/10.1109/CVPR.2016.308
  31. Taheri Hajivand, A., Shirini, K., and Samadi Gharehveran, S. 2024. Weed detection in cereal fields using convolutional neural network based on deep learning. Agricultural Engineering (Scientific Journal of Agriculture), 47(1): 129-142. https:// doaj.org/10.22055/agen.2024.45449.1697
  32. Tanaka, M. 2020. Weighted sigmoid gate unit for an activation function of deep neural network. Pattern Recognition Letters, 135: 354–359. https://doi.org/10.1016/j.patrec.2020.05.017
  33. Taner, Y., Öztekin, B., Tekgüler, A., Sauk, H., and Duran, H. 2018. Classification of Varieties of Grain Species by Artificial Neural Networks. Agronomy, 8: 123. https://doi.org/10.3390/agronomy8070123
  34. Tu, K., Wen, S., Cheng, Y., Zhang, T., Pan, T., Wang, J., Wang, J., and Sun, Q. 2021. A Non-Destructive and Highly Efficient Model for Detecting the Genuineness of Maize Variety ‘JINGKE 968’ Using Machine Vision Combined with Deep Learning. Computers and Electronics in Agriculture, 182: 106002. https://doi.org/10.1016/j.compag.2021.106002
  35. Vishnoi, V., Kumar, K., Kumar, B., Mohan, S., and Khan, A. 2023. Detection of Apple Plant Diseases Using Leaf Images Through Convolutional Neural Network. IEEE Access, 11: 6594–6609. https://doi.org/10.1109/ACCESS.2022.3232917
  36. Von Chamier, L., Laine, R. F., Jukkala, J., Spahn, C., Krentzel, D., Nehme, E., Lerche, M., Hernández-Pérez, S., Mattila, P. K., Karinou, E., Holden, S., Solak, A. C., Krull, A., Buchholz, T.-O., Jones, M. L., Royer, L. A., Leterrier, C., Shechtman, Y., Jug, F., Heilemann, M., Jacquemet, G., and Henriques, R. 2021. Democratising deep learning for microscopy with ZeroCostDL4Mic. Nature Communications, 12(1): 2276. https://www.nature.com/articles/s41467-021-22518-0.
  37. Wang, P., Fan, E., and Wang, P. 2021. Comparative analysis of image classification algorithms based on traditional machine learning and deep learning. Pattern Recognition Letters, 141: 61–67. https://linkinghub.elsevier.com/retrieve/pii/S0167865520302981.
  38. Wang, Y.-H., and Su, W.-H. 2022. Convolutional Neural Networks in Computer Vision for Grain Crop Phenotyping: A Review. Agronomy, 12: 2659. https://doi.org/10.3390/agronomy12112659
  39. Windarto, A. P., Wanto, A., Solikhun, S., and Watrianthos, R. 2023. A Comprehensive Bibliometric Analysis of Deep Learning Techniques for Breast Cancer Segmentation: Trends and Topic Exploration (2019-2023). Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), 7(5): 1155–1164. https://doi.org/10.29207/resti.v7i5.4684
  40. Xia, C., Yang, S., Huang, M., Zhu, Q., Guo, Y., and Qin, J. 2019. Maize Seed Classification Using Hyperspectral Image Coupled with Multi-Linear Discriminant Analysis. Infrared Physics and Technology, 103: 103077. https://doi.org/10.1016/j.infrared.2019.103077
  41. Xu, P., Tan, Q., Zhang, Y., Zha, X., Yang, S., and Yang, R. 2022. Research on Maize Seed Classification and Recognition Based on Machine Vision and Deep Learning. Agriculture, 12: 232. https://doi.org/10.3390/agriculture12020232
  42. Xu, P., Yang, R., Zeng, T., Zhang, J., Zhang, Y., and Tan, Q. 2021. Varietal Classification of Maize Seeds Using Computer Vision and Machine Learning Techniques. Journal of Food Process Engineering, 44: e13846. https://doi.org/10.1111/jfpe.13846
  43. Zhao, J., Liu, C., Han, J., Zhou, Y., Li, Y., and Zhang, L. 2025. Real-Time Corn Variety Recognition Using an Efficient DenXt Architecture with Lightweight Optimizations. Agriculture, 15(1): 79 https://doi.org/10.3390/agriculture15010079
  44. Afifi, M. R., Mansoori, Y., zaki dizaji, H. and Akbarizadeh, G. 2018. Grading zahedi dates based on external features using image processing and machine learning methods. Agricultural Engineering, 41(3): 73-84. doi: 10.22055/agen.2019.23352.1374
Agricultural Engineering
Volume 48, Issue 4
December
Autumn 2026
Pages 609-589

Home

Submit Manuscript

Editorial Staff

Editorial Board

Publication Ethics

Guide for Authors

Article Processing Charges

Reviewers

contact us