Dimensionality-Aware Dry Bean Classification Using Transfer Learning and SVM: Addressing Variety and Resolution Constraints
DOI:
https://doi.org/10.62411/faith.3048-3719-140Keywords:
Classification of dry beans, Dimensionality-aware, InceptionV3, Principal component analysis (PCA), Support vector machine (SVM)Abstract
Accurate classification of dry bean varieties is essential for enhancing agricultural productivity, ensuring seed quality, and supporting market standardization. Traditional classification methods are time-consuming, labor-intensive, and prone to error, particularly when dealing with morphologically similar varieties. While recent data-driven approaches have shown promising performances, they often suffer from limited varietal representation, inadequate handling of high-resolution image data, and suboptimal dimensionality reduction techniques. To address these challenges, this study proposes a novel hybrid classification pipeline that integrates a fine-tuned InceptionV3 for low- and high-level feature extraction, Principal Component Analysis (PCA) for efficient dimensionality reduction, and a Support Vector Machine (SVM) for final classification. The model was evaluated on a comprehensive dataset combining 14 dry bean varieties from Dogan et al. with five locally sourced varieties, totaling 19 distinct classes. Extensive experimental results showed that the proposed model achieved an accuracy of 94.00% and 80.01% on benchmark and combined datasets, respectively, outperforming state-of-the-art approaches.
Downloads
References
D. A. Luna-Vital, L. Mojica, E. González de Mejía, S. Mendoza, and G. Loarca-Piña, “Biological potential of protein hydrolysates and peptides from common bean (Phaseolus vulgaris L.): A review,” Food Res. Int., vol. 76, pp. 39–50, Oct. 2015, doi: 10.1016/j.foodres.2014.11.024.
M. Siddiq and M. A. Uebersax, “Dry Beans and Pulses Production and Consumption—An Overview,” in Dry Beans and Pulses Production, Processing and Nutrition, Wiley, 2012, pp. 1–22. doi: 10.1002/9781118448298.ch1.
E. Ceyhan, A. Kahraman, and M. Onder, “The Impacts of Environment on Plant Products,” Int. J. Biosci. Biochem. Bioinforma., pp. 48–51, 2012, doi: 10.7763/IJBBB.2012.V2.68.
M. Dogan, Y. S. Taspinar, I. Cinar, R. Kursun, I. A. Ozkan, and M. Koklu, “Dry bean cultivars classification using deep cnn features and salp swarm algorithm based extreme learning machine,” Comput. Electron. Agric., vol. 204, p. 107575, Jan. 2023, doi: 10.1016/j.compag.2022.107575.
G. Shobana, S. N. Bushra, K. U. Maheswari, and N. Subramanian, “Multivariate Classification of Dry Beans using Pipelined Dimensionality Reduction Technique,” in 2022 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), Jul. 2022, pp. 1–6. doi: 10.1109/ICSES55317.2022.9914079.
F. M. Firnando, D. R. I. M. Setiadi, A. R. Muslikh, and S. W. Iriananda, “Analyzing InceptionV3 and InceptionResNetV2 with Data Augmentation for Rice Leaf Disease Classification,” J. Futur. Artif. Intell. Technol., vol. 1, no. 1, pp. 1–11, May 2024, doi: 10.62411/faith.2024-4.
S. S. Chawathe, “Classification of Dry Beans Using Image Features,” in 2021 IEEE 12th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), Dec. 2021, pp. 0950–0956. doi: 10.1109/UEMCON53757.2021.9666732.
C. H. Mendigoria et al., “Seed Architectural Phenes Prediction and Variety Classification of Dry Beans (Phaseolus vulgaris) Using Machine Learning Algorithms,” in 2021 IEEE 9th Region 10 Humanitarian Technology Conference (R10-HTC), Sep. 2021, pp. 01–06. doi: 10.1109/R10-HTC53172.2021.9641554.
Y. S. Taspinar, M. Dogan, I. Cinar, R. Kursun, I. A. Ozkan, and M. Koklu, “Computer vision classification of dry beans (Phaseolus vulgaris L.) based on deep transfer learning techniques,” Eur. Food Res. Technol., vol. 248, no. 11, pp. 2707–2725, Nov. 2022, doi: 10.1007/s00217-022-04080-1.
A. Mehta, P. Sengupta, D. Garg, H. Singh, and Y. S. Diamand, “Benchmarking the Effectiveness of Classification Algorithms and SVM Kernels for Dry Beans,” arXiv. Jul. 15, 2023. [Online]. Available: http://arxiv.org/abs/2307.07863
M. Salauddin Khan et al., “Comparison of multiclass classification techniques using dry bean dataset,” Int. J. Cogn. Comput. Eng., vol. 4, pp. 6–20, Jun. 2023, doi: 10.1016/j.ijcce.2023.01.002.
J. C. Macuácua, J. A. S. Centeno, and C. Amisse, “Data mining approach for dry bean seeds classification,” Smart Agric. Technol., vol. 5, p. 100240, Oct. 2023, doi: 10.1016/j.atech.2023.100240.
P. J. M. Michael, M. Hussein, A. S. Camilius, R. M. Richard, M. Beatrice, and M. Caroline, “Artificial intelligence and deep learning based technologies for emerging disease recognition and pest prediction in beans (phaseolus vulgaris l.): A systematic review,” African J. Agric. Res., vol. 19, no. 3, pp. 260–271, Mar. 2023, doi: 10.5897/AJAR2022.16226.
N. K. Naik, P. K. Sethy, R. Amat, S. K. Behera, and P. Biswas, “Evaluation of optimization techniques with support vector machine for identification of dry beans,” Indones. J. Electr. Eng. Comput. Sci., vol. 32, no. 2, p. 704, Nov. 2023, doi: 10.11591/ijeecs.v32.i2.pp704-714.
H. Vaidya, K. V. Prasad, R. S, and K. K. Swamy, “Multiclass Classification of Dry Beans using Artificial Neural Network,” J. Int. Acad. Phys. Sci., vol. 27, no. 2, pp. 109–124, 2023, [Online]. Available: https://www.iaps.org.in/journal/index.php/journaliaps/article/view/994
M. V. Subbarao, J. T. S. Sindhu, Y. C. A. Padmanabha Reddy, V. Ravuri, K. P. Vasavi, and G. C. Ram, “Performance Analysis of Feature Selection Algorithms in the Classification of Dry Beans using KNN and Neural Networks,” in 2023 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS), Mar. 2023, pp. 539–545. doi: 10.1109/ICSCDS56580.2023.10104809.
L. Volpato, E. M. Wright, S. Bales, and F. E. Gomez, “A retrospective analysis of historical data of multi‐environment trials for dry bean ( Phaseolus vulgaris L.) in Michigan,” Crop Sci., vol. 64, no. 2, pp. 631–650, Mar. 2024, doi: 10.1002/csc2.21184.
L. F. Justino, A. B. Heinemann, D. H. da Matta, L. F. Stone, P. A. de O. Gonçalves, and S. C. da Silva, “Characterization of common bean production regions in Brazil using machine learning techniques,” Agric. Syst., vol. 224, p. 104237, Mar. 2025, doi: 10.1016/j.agsy.2024.104237.
A. Mukherjee et al., “SMOTE-ENN resampling technique with Bayesian optimization for multi-class classification of dry bean varieties,” Appl. Soft Comput., vol. 181, p. 113467, Sep. 2025, doi: 10.1016/j.asoc.2025.113467.
T. J. Adejumo, A. I. Okegbade, E. T. Adewuyi, O. O. Shadare, and O. O. Oladiran, “Classification of Beans Using Principal Component Analysis: An Unsupervised Learning Classification Approach,” Int. J. Math. Comput. Methods, vol. 10, pp. 148–165, 2025.
Y. Kumar, N. Hasteer, A. Bhardwaj, and . Yogesh, “Convolutional neural network architecture for detection and classification of diseases in fruits,” Curr. Sci., vol. 122, no. 11, p. 1315, Jun. 2022, doi: 10.18520/cs/v122/i11/1315-1320.
M. Gong, “A Novel Performance Measure for Machine Learning Classification,” Int. J. Manag. Inf. Technol., vol. 13, no. 1, pp. 11–19, Feb. 2021, doi: 10.5121/ijmit.2021.13101.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Ahmad Khamis, Ashraf Ishaq, Martins E. Irhebhude, D.T. Chinyio
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
