Vol. 2 No. 2 (2026): Vol 2 No 2 (November 2026)
Articles

Comparative Performance Analysis of CNN Architectures for Coffee Bean Image Classification Based on Accuracy and Training Time

PDF
  • Nazwa Firyal Cherry,
  • Nurwahida Zakia,
  • Hani Uliya Pasya
Nazwa Firyal Cherry
Politeknik Negeri lhokseumawe
Nurwahida Zakia
Politeknik Negeri lhokseumawe
Hani Uliya Pasya
UIN Syarif Hidayatullah Jakarta

Published 08-11-2026

Keywords

  • Coffee Bean Image Classification,
  • Deep Learning,
  • Transfer Learning,
  • Model Performance Evaluation,
  • Training Time Efficiency

Copyright (c) 2026 Nazwa Firyal Cherry, Nurwahida Zakia, Hani Uliya Pasya (Author)

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Abstract

Coffee bean image classification is an application of computer vision that can support the automated identification and quality categorization of coffee beans. This study aims to compare the performance of several Convolutional Neural Network (CNN) models, namely MobileNetV2, ResNet50, EfficientNetB0, VGG16, and DenseNet121, for coffee bean image classification. The dataset consists of coffee bean images that underwent preprocessing and data splitting for model training and testing. Model performance was evaluated based on classification accuracy and training time. The results show that MobileNetV2 achieved the best performance, with an accuracy of 98.75% and the shortest training time of 97.69 seconds. DenseNet121 also achieved high accuracy of 98.25%, with a training time of 230.96 seconds. Meanwhile, VGG16 achieved an accuracy of 89.00% but required the longest training time of 491.79 seconds. ResNet50 and EfficientNetB0 demonstrated comparatively lower performance, with accuracies of 63.75% and 25.00%, respectively. Based on these findings, MobileNetV2 can be recommended as the most effective model for coffee bean image classification, as it provides a favorable balance between high classification accuracy and training efficiency.

PDF

Downloads

Download data is not yet available.

References

  1. [1] Pratama, G. A., Puspaningrum, E. Y., & Maulana, H. (2024). "Convolutional Neural Network dan Faster Region Convolutional Neural Network untuk Klasifikasi Kualitas Biji Kopi Arabika." Jurnal Informatika dan Teknik Elektro Terapan (JITET), 12(3).
  2. [2] Murinto, M., Rosyda, M., & Melany, M. (2023). "Klasifikasi Jenis Biji Kopi Menggunakan Convolutional Neural Network dan Transfer Learning pada Model VGG16 dan MobileNetV2." JRST (Jurnal Riset Sains dan Teknologi), 7(2), 183-189.
  3. [3] Hibatullah, A. A., Asriyanik, A., & Apriandari, W. (2024). "Klasifikasi Kualitas Jenis Kopi Halus Robusta Menggunakan Convolutional Neural Network (CNN) dan Mobilenet-V2." JATI (Jurnal Mahasiswa Teknik Informatika), 8(5), 8650-8657.
  4. [4] Putra, K. U., et al. (2024). "Identifikasi Varietas Kopi Berdasarkan Analisis Warna dan Tekstur Menggunakan Metode Convolutional Neural Network." Bulletin of Computer Science Research.
  5. [5] Putra, F. D. B. S. (2023). "Klasifikasi Tingkat Roasting Biji Kopi Berbasis Citra dengan CNN." Jurnal Teknologi Informasi, Universitas Teknologi Digital Indonesia.
  6. [6] Rahmawati, A., et al. (2024). "Penerapan Arsitektur U-Net pada Segmentasi Cacat Biji Kopi untuk Optimalisasi Inspeksi Kualitas." Jurnal Ilmu Komputer dan Sistem Informasi, 5(2).
  7. [7] Yuliyanti, S., et al. (2024). "Multi-Class Real-Time Color Classification of Coffee Beans via Fine-Tuned EfficientNetB0 and Post-Training Quantization." Jurnal Teknik Informatika (Jutif).
  8. [8] Juarto, B., et al. (2024). "Mobile Deep Learning-Based Coffee Bean Quality Classification and Smartphone Integration Using Transfer Learning." SISFO.
  9. [9] Ardian, Y., et al. (2024). "Comparative Performance Analysis of Modified VGG16 and Slim-CNN for Arabica Coffee Bean Defect Classification." ILKOM Jurnal Ilmiah.
  10. [10] Peryanto, A., Yudhana, A., & Umar, R. (2019). "Rancang Bangun Klasifikasi Citra Dengan Teknologi Deep Learning Berbasis Metode Convolutional Neural Network." Jurnal Ilmiah Teknik Informatika (FORMAT), 8(2), 139-140.
  11. [11] Santoso, B. R., Sari, C. A., & Rachmawanto, E. H. (2025). "Coffee Beans Classification Using Convolutional Neural Networks Based On Extraction Value Analysis In Grayscale Color Space." Journal of Applied Informatics and Computing, 9(1), 31-37.
  12. [12] Tamayo-Monsalve, M. A., et al. (2022). "Coffee Maturity Classification Using Convolutional Neural Networks and Transfer Learning." IEEE Access, 10, 42971-42982.
  13. [13] Chang, S., & Huang, C. (2021). "Deep Learning Model for the Inspection of Coffee Bean Defects." Applied Sciences, 11(17), 8226.
  14. [14] Chou, Y., et al. (2019). "Deep Learning Model for Defective Bean Inspection with GAN‐Structured Automated Labeled Data Augmentation in Coffee Industry." Applied Sciences, 9(19), 4166.
  15. [15] Arwatchananukul, S., et al. (2024). "Implementing a Deep Learning Model for Defect Classification in Thai Arabica Green Coffee Beans." Smart Agricultural Technology, 9, 100680.
  16. [16] Muchtar, M., et al. (2025). "Edge AI-Based Detection for Defective Coffee Beans Using Deep Learning and Streamlit Framework." IEEE Access, 13, 67977-67992.
  17. [17] Hsia, C. H. (2021). "Deep Convolutional Neural Network for Coffee Bean Inspection." Sensors and Materials, 33(9).
  18. [18] Putra, B. T. W., Amirudin, R., & Marhaenanto, B. (2022). "The Evaluation of Deep Learning Using Convolutional Neural Network (CNN) Approach for Identifying Arabica and Robusta Coffee Plants." Journal of Biosystems Engineering, 47(2), 118-129.