On the Effectiveness of Lightweight CNN Architectures for Fine-Grained Coffee Bean Classification

Akbar Muhamad Burhanudhin; Usman Sudibyo; Eka Putra Agus Meindiawan

doi:10.29408/edumatic.v10i1.34044

Authors

Akbar Muhamad Burhanudhin Universitas Dian Nuswantoro https://orcid.org/0009-0009-0256-2713
Usman Sudibyo https://orcid.org/0009-0008-6853-3969
Eka Putra Agus Meindiawan Universitas Dian Nuswantoro https://orcid.org/0009-0004-1251-8226

DOI:

https://doi.org/10.29408/edumatic.v10i1.34044

Keywords:

cnn, coffee bean, deep learning, efficientnetb0, mobilenetv2

Abstract

Distinguishing coffee bean varieties remains a significant challenge in the agricultural industry due to high inter-class similarity and the subtle morphological differences between species. This study aims to conduct a comparative evaluation of MobileNetV2 and EfficientNetB0 for fine-grained coffee bean classification, specifically investigating how efficiency-oriented architectural mechanisms such as depthwise separable convolution and compound scaling influence feature extraction. The research employed a quantitative experimental method using a private dataset of 2,400 images comprising Arabica, Robusta, and Liberica varieties. Data preprocessing included resizing to 224×224 pixels and augmentation, followed by training the two architectures using transfer learning under a controlled experimental framework. The results showed that EfficientNetB0 achieved superior performance with a testing accuracy of 99.17%, while MobileNetV2 attained a competitive accuracy of 98.33% with lower computational complexity. These results demonstrate that while EfficientNetB0 is optimal for high-precision industrial sorting, MobileNetV2 offers a highly efficient alternative for resource-constrained mobile applications. This study provides a scalable framework for automating quality control, effectively balancing architectural efficiency with the sensitivity required for accurate coffee variety identification.

References

Aldea, C. L., Bocu, R., & Solca, R. N. (2023). Real-Time Monitoring and Management of Hardware and Software Resources in Heterogeneous Computer Networks through an Integrated System Architecture. Symmetry, 15(6). https://doi.org/10.3390/sym15061134

Alimova, I., Tutubalina, E., & Nikolenko, S. I. (2022). Cross-Domain Limitations of Neural Models on Biomedical Relation Classification. IEEE Access, 10, 1432–1439. https://doi.org/10.1109/ACCESS.2021.3135381

Anto, I. A. F., Wibowo, J. W., Munandar, A., & Salim, T. I. (2025). Comparative performance analysis of convolutional neural network-architectures on coffee-bean roast classification. TELKOMNIKA (Telecommunication Computing Electronics and Control), 23(6), 1590-1599. https://doi.org/10.12928/telkomnika.v23i6.27090

Bera, A., Nasipuri, M., Krejcar, O., & Bhattacharjee, D. (2023). Fine-Grained Sports, Yoga, and Dance Postures Recognition: A Benchmark Analysis. IEEE Transactions on Instrumentation and Measurement, 72(0), 1–12. https://doi.org/10.1109/TIM.2023.3293564

Bhagat, D., Vakil, A., Gupta, R. K., & Kumar, A. (2024). Facial Emotion Recognition (FER) using Convolutional Neural Network (CNN). Procedia Computer Science, 235(2023), 2079–2089. https://doi.org/10.1016/j.procs.2024.04.197

Bian, J., Arafat, A. Al, Xiong, H., Li, J., Li, L., Chen, H., Wang, J., Dou, D., & Guo, Z. (2022). Machine Learning in Real-Time Internet of Things (IoT) Systems: A Survey. IEEE Internet of Things Journal, 9(11), 8364–8386. https://doi.org/10.1109/JIOT.2022.3161050

Binning, S. A., Ackerly, K. L., Cooke, S. J., Fusi, M., Gomez Isaza, D. F., Hardison, E. A., Martin, S., Munson, A., Pineda, M., Schwieterman, G. D., Reichard, M., Rummel, A., & Blewett, T. A. (2025). The lab-field continuum in conservation physiology research: leveraging multiple approaches to inform policy and practice. Conservation Physiology, 13(1), 1–14. https://doi.org/10.1093/conphys/coaf063

Corthis, P. B., Ramesh, G. P., García-Torres, M., & Ruíz, R. (2024). Effective Identification and Authentication of Healthcare IoT Using Fog Computing with Hybrid Cryptographic Algorithm. Symmetry, 16(6). https://doi.org/10.3390/sym16060726

Fareed, M. M. S., Zikria, S., Ahmed, G., Mui-Zzud-Din, Mahmood, S., Aslam, M., Jillani, S. F., Moustafa, A., & Asad, M. (2022). ADD-Net: An Effective Deep Learning Model for Early Detection of Alzheimer Disease in MRI Scans. IEEE Access, 10, 96930–96951. https://doi.org/10.1109/ACCESS.2022.3204395

González-Briones, A., Florez, S. L., Chamoso, P., Castillo-Ossa, L. F., & Corchado, E. S. (2025). Enhancing Plant Disease Detection: Incorporating Advanced CNN Architectures for Better Accuracy and Interpretability. International Journal of Computational Intelligence Systems, 18(1). https://doi.org/10.1007/s44196-025-00835-2

Hassan, E. (2024). Enhancing coffee bean classification: a comparative analysis of pre-trained deep learning models. Neural Computing and Applications, 36(16), 9023–9052. https://doi.org/10.1007/s00521-024-09623-z

Issitt, R. W., Cortina-Borja, M., Bryant, W., Bowyer, S., Taylor, A. M., & Sebire, N. (2022). Classification Performance of Neural Networks Versus Logistic Regression Models: Evidence From Healthcare Practice. Cureus, 14(2), 1–8. https://doi.org/10.7759/cureus.22443

Kansal, K., Chandra, T. B., & Singh, A. (2024). ResNet-50 vs. EfficientNet-B0: Multi-Centric Classification of Various Lung Abnormalities Using Deep Learning “session id: ICMLDsE.004.” Procedia Computer Science, 235, 70–80. https://doi.org/10.1016/j.procs.2024.04.007

Korkmaz, A., Talan, T., Koşunalp, S., & Iliev, T. (2025). Comparison of deep learning models in automatic classification of coffee bean species. PeerJ Computer Science, 11, 1–29. https://doi.org/10.7717/peerj-cs.2759

Lambert, B., Forbes, F., Doyle, S., Dehaene, H., & Dojat, M. (2024). Trustworthy clinical AI solutions: A unified review of uncertainty quantification in Deep Learning models for medical image analysis. Artificial Intelligence in Medicine, 150, 102830. https://doi.org/10.1016/j.artmed.2024.102830

Li, W., Fan, Z., Huo, J., & Gao, Y. (2023). Modeling Inter-Class and Intra-Class Constraints in Novel Class Discovery. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2023-June, 3449–3458. https://doi.org/10.1109/CVPR52729.2023.00336

Liu, S., Zhong, W., Guo, F., Cong, J., & Gu, B. (2024). Fine-Grained Few-Shot Image Classification Based on Feature Dual Reconstruction. Electronics (Switzerland), 13(14). https://doi.org/10.3390/electronics13142751

Lu, J., Zhang, W., Zhao, Y., & Sun, C. (2022). Image local structure information learning for fine-grained visual classification. Scientific Reports, 12(1), 1–10. https://doi.org/10.1038/s41598-022-23835-0

Ni, X., Wang, F., Huang, H., Wang, L., Wen, C., & Chen, D. (2024). A CNN- and Self-Attention-Based Maize Growth Stage Recognition Method and Platform from UAV Orthophoto Images. Remote Sensing, 16(14). https://doi.org/10.3390/rs16142672

Pan, Q., Liu, K., Zheng, S., & Wang, G. (2025). A Fine-Grained Image Classification Method Based on ConvNeXt Heatmap Localization and Contrastive Learning. IEEE Access, 80123–80132. https://doi.org/10.1109/ACCESS.2025.3567488

Raja, S. P., Sawicka, B., Stamenkovic, Z., & Mariammal, G. (2022). Crop Prediction Based on Characteristics of the Agricultural Environment Using Various Feature Selection Techniques and Classifiers. IEEE Access, 10, 23625–23641. https://doi.org/10.1109/ACCESS.2022.3154350

Shao, Y., Li, L., Li, J., Li, Q., An, S., & Hao, H. (2024). Out-of-plane full-field vibration displacement measurement with monocular computer vision. Automation in Construction, 165, 105507. https://doi.org/10.1016/j.autcon.2024.105507

Shin, J., Kaneko, Y., Miah, A. S. M., Hassan, N., & Nishimura, S. (2024). Anomaly Detection in Weakly Supervised Videos Using Multistage Graphs and General Deep Learning Based Spatial-Temporal Feature Enhancement. IEEE Access, 12(March), 65213–65227. https://doi.org/10.1109/ACCESS.2024.3395329

Strelcenia, E., & Prakoonwit, S. (2023). Improving Cancer Detection Classification Performance Using GANs in Breast Cancer Data. IEEE Access, 11, 71594–71615. https://doi.org/10.1109/ACCESS.2023.3291336

Tan, M., & Le, Q. V. (2021). EfficientNetV2: Smaller Models and Faster Training. Proceedings of Machine Learning Research, 139, 10096–10106.

Valarmathi, B., Srinivasa Gupta, N., Prakash, G., Hemadri Reddy, R., Saravanan, S., & Shanmugasundaram, P. (2023). Hybrid Deep Learning Algorithms for Dog Breed Identification - A Comparative Analysis. IEEE Access, 77228–77239. https://doi.org/10.1109/ACCESS.2023.3297440

Yaseliani, M., Hamadani, A. Z., Maghsoodi, A. I., & Mosavi, A. (2022). Pneumonia Detection Proposing a Hybrid Deep Convolutional Neural Network Based on Two Parallel Visual Geometry Group Architectures and Machine Learning Classifiers. IEEE Access, 10, 62110–62128. https://doi.org/10.1109/ACCESS.2022.3182498

Zhao, X., Wang, L., Zhang, Y., Han, X., Deveci, M., & Parmar, M. (2024). A review of convolutional neural networks in computer vision. Artificial Intelligence Review, 57(4). Springer Netherlands. https://doi.org/10.1007/s10462-024-10721-6