High-Accuracy Real-Time Defect Classification for Coffee Beans Using Deep Learning

References

[1] N. Zhao et al., “OGS-YOLOv8: Coffee bean maturity detection algorithm based on improved YOLOv8,” Applied Sciences, vol. 15, no. 21, 2025.

[2] E. D. Nugroho, M. Verdiana, M. H. Algifari, A. A. Rizkita, R. A. Winarta and D. Gunawan, “Development of YOLO-based mobile application for detection of defect types in robusta coffee beans,” Journal of Applied Informatics and Computing, vol. 9, no. 1, pp. 153–160, 2025.

[3] T. A. Tarekegn and T. G. Debelee, “KN-YOLOv8: A lightweight deep learning model for real-time coffee bean defect detection,” SSRN Preprint, 2025.

[4] X. Hu, “Siamese networks for few-shot coffee bean defect detection,” Computers & Electronics in Agriculture, 2025.

[5] J. J. M. Reales, R. N. Mendoza and V. D. Labas, “Green coffee bean quality inspection using computer vision systems,” Proc. IEICES International Exchange and Innovation Conference on Engineering & Sciences, 2024.

[6] H. L. Gope, H. Fukai, F. M. Ruhad and S. Barman, “Comparative analysis of YOLO models for green coffee bean detection and defect classification,” Scientific Reports, vol. 14, 28946, 2024.

[7] X. Hu et al., “Coffee green bean defect detection method based on an improved YOLO architecture,” Mathematical Problems in Engineering, 2024.

[8] N. O. Adiwijaya, D. R. Wijaya and R. Sarno, “Coffee defects detection based on green bean images using YOLO architecture,” Proc. IEEE ICEECIT, 2024.

[9] Gheorghiu et al., “Evaluating data augmentation techniques for coffee leaf disease classification,” arXiv Preprint, 2024.

[10] A.D. Putra and G. E. Saputra, “Implementation of YOLOv8 algorithm for web-based detection of coffee fruit ripeness,” Journal of Artificial Intelligence and Software Engineering, 2025.

[11] V. Amadea, R. Rachmawati et al., “Defect detection in Arabica green coffee beans using DEtection architecture,” ACM Conference Proceedings, 2024.

[12] X. Zuo, J. Dong, Y. Gao and Z. Wu, “HyperDefect- YOLO: Enhancing YOLO with hypergraph computation for industrial defect detection,” arXiv Preprint, 2024.

[13] S. Kumar S., A. K. M. Ajmal Khan, I. A. Banday, M. Gada and V. V. Shanbhag, “Overcoming agricultural LLM challenges using RAG-driven precision for crop disease remediation,” arXiv Preprint, 2024.

[14] M. García et al., “Quality and defect inspection of green coffee beans using image processing and machine learning,” Applied Sciences, vol. 9, no. 19, 2019.

[15] E. I. Arboleda, “Deep learning model for inspection of coffee bean defects,” Applied Sciences, vol. 11, no. 17, 2021.

@article{1712938,
      author = {Archana N, Mahalaksmi, C G Yashasraj, Prajwal S B},
      title = {High-Accuracy Real-Time Defect Classification for Coffee Beans Using Deep Learning},
      journal = {Iconic Research And Engineering Journals},
      year = {2025},
      volume = {9},
      number = {6},
      pages = {1350-1355},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1712938.pdf},
      abstract = {Consistent quality inspection of coffee beans remains a critical requirement in the agricultural supply chain, as manual sorting is slow, inconsistent, and dependent on worker experience. With recent advancements in deep learning, real-time object recognition models provide an opportunity to automate quality assessment with high accuracy and minimal intervention. This study presents a YOLOv8-based computer vision system designed to detect and classify defective coffee beans, including broken, discolored, insect-damaged, and mold-affected samples. The proposed model is trained on an annotated dataset of roasted and unroasted beans under varying illumination and background conditions. The system demonstrates strong generalization capability, outperforming traditional CNN classification systems in speed and reliability, achieving up to 97.8% detection accuracy at 60 FPS on GPU inference. The study concludes that YOLOv8 can significantly improve the speed and precision of coffee quality analysis, enabling fully automated grading lines for industrial deployment.[2]},
      keywords = {Computer Vision, Coffee Quality Inspection, YOLOv8, Deep Learning, Defect Detection, Industrial Automation.},
      month = {December},
      doi = {https://doi.org/10.64388/IREV9I6-1712938}
  }