SavedAdd your journal

Journals / Endüstri Mühendisliği / 2026 / Cilt: 37 Sayı: 2

DETECTION OF DEFECTS IN THE FOOD INDUSTRY USING DEEP LEARNING MODELS

DERİN ÖĞRENME MODELLERİ KULLANILARAK GIDA ENDÜSTRİSİNDE KUSUR TESPİTİ

Asena Begüm Tiryaki Şahin(SAMSUN ÜNİVERSİTESİ)0009-0001-1637-1581
Ebru Pekel Özmen(Samsun Üniversitesi)0000-0001-7717-6790
Pages
504–534
Publication Date
2026-08-28
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The results indicate that deep learning methods can effectively distinguish between defective and non-defective products, with some architectures achieving high accuracy and strong generalization capability.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:This study explores the use of deep learning for automated defect detection in chocolate bar coatings prior to packaging.
📊
Key Findings & Data:Model performance was evaluated through five-fold cross-validation, employing standard metrics such as Accuracy, Precision, Recall, and F1-score.
💡
Conclusion & Impact:The results indicate that deep learning methods can effectively distinguish between defective and non-defective products, with some architectures achieving high accuracy and strong generalization capability.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Derin Öğrenme · Transfer Öğrenme · Kusur Tespiti

Abstract

This study explores the use of deep learning for automated defect detection in chocolate bar coatings prior to packaging. A dataset collected from the production line was analyzed using transfer learning with multiple pre-trained convolutional neural networks. Model performance was evaluated through five-fold cross-validation, employing standard metrics such as Accuracy, Precision, Recall, and F1-score. The results indicate that deep learning methods can effectively distinguish between defective and non-defective products, with some architectures achieving high accuracy and strong generalization capability. These findings demonstrate the potential of artificial intelligence to enhance quality assurance processes in food manufacturing, enabling more reliable and efficient production systems.

Özet

Bu çalışma, paketleme öncesi çikolata bar kaplamalarındaki kusurların otomatik olarak tespit edilmesinde derin öğrenmenin kullanımını incelemektedir. Üretim hattından toplanan bir veri kümesi, önceden eğitilmiş evrişimsel sinir ağlarıyla transfer öğrenme kullanılarak analiz edilmiştir. Model performansı, beş katlı çapraz doğrulama ile değerlendirilmiş ve Doğruluk, Kesinlik, Duyarlılık ve F1-skoru gibi standart metrikler kullanılmıştır. Sonuçlar, derin öğrenme yöntemlerinin kusurlu ve kusursuz ürünleri etkin bir şekilde ayırt edebildiğini; bazı mimarilerin ise yüksek doğruluk ve güçlü genelleme kabiliyeti sergilediğini göstermektedir. Bu bulgular, yapay zekânın gıda üretiminde kalite güvence süreçlerini geliştirme potansiyeline sahip olduğunu, daha güvenilir ve verimli üretim sistemlerine olanak sağladığını ortaya koymaktadır.

🔖

Cite This Article

Şahin, A. B. T., Özmen, E. P. (2026). DETECTION OF DEFECTS IN THE FOOD INDUSTRY USING DEEP LEARNING MODELS. Endüstri Mühendisliği, Cilt: 37 Sayı: 2, 504–534. https://doi.org/10.46465/endustrimuhendisligi.1784421

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (53)

  1. Ali, A., Shahbaz, H., & Damaševičius, R. (2025). xCViT: Improved Vision Transformer Network with Fusion of CNN and Xception for Skin Disease Recognition with Explainable AI. Computers, Materials & Continua, 83(1), 1367-1398. Doi: https://doi.org/10.32604/cmc.2025.059301
  2. Alom, M. Z., Hasan, M., Yakopcic, C., Taha, T. M., & Asari, V. K. (2020). Improved inception-residual convolutional neural network for object recognition. Neural Computing and Applications, 32(1), 279-293. Doi: https://doi.org/10.1007/s00521-018-3627-6
  3. Arima, K., Nakashima, K., Miki, K., Nagata, F., & Watanabe, K. (2020). Detection of Defective Wrap Roll Product Using Transfer Learning of Convolution Neural Networks-Design and evaluation of CNNs by transfer learning of Inseption V3. 計測自動制御学会システムインテグレーション部門講演会 (CD-ROM), 21, 3-9.
  4. Baldassarre, F., Morín, D. G., & Rodés-Guirao, L. (2017). Deep koalarization: Image colorization using cnns and inception-resnet-v2. arXiv preprint arXiv:1712.03400. Retrieved from https://arxiv.org/abs/1712.03400
  5. Birsen, S. (2025). Detection and classification of fabric defects with an innovative model and perspective (Master's thesis). Istanbul Technical University, Graduate School, İstanbul, Turkey.
  6. Bıyıklı, Y. (2025). Artificial intelligence detection of steel surface defects (Master's thesis). Zonguldak Bülent Ecevit University, Graduate School of Natural and Applied Sciences, Zonguldak, Turkey.
  7. Boyacıgil, M. F. (2022). Görüntü işleme teknikleriyle bir endüstriyel kalite kontrol uygulaması [An industrial quality control application using image processing techniques] (Master's thesis). Necmettin Erbakan University, Konya, Turkey.
  8. Das, S., Jayakumar, J., Banerjee, S., Ramaswamy, J., Vangala, V., Ram, K., & Mitra, P. (2019). High precision automated detection of labeled nuclei in gigapixel resolution image data of mouse brain. bioRxiv, 252247.
  9. Demir, M. (2025). A deep learning assisted approach for plasterboard edge defects (Master's thesis). Çankırı Karatekin University, Graduate School of Natural and Applied Sciences, Çankırı, Turkey.
  10. Diogo, A. R., Moreira, B., Gouveia, C. A., & Tavares, J. M. R. (2022). A review of signal processing techniques for ultrasonic guided wave testing. Metals, 12(6), 936. Doi: https://doi.org/10.3390/met12060936
  11. Ferguson, M. K., Ronay, A., Lee, Y. T., & Law, K. H. (2018). Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learning. Smart Sustain Manuf Syst, 2. Doi: https://doi.org/10.1520/SSMS20180033
  12. Hossain, A. A., Nisha, J. K., & Johora, F. (2023). Breast cancer classification from ultrasound images using transfer learning based on VGG16 model. International Journal of Image, Graphics and Signal Processing, 15(1), 12-22. Doi: https://doi.org/10.5815/ijigsp.2023.01.02
  13. Jiao, R., Liu, Y., He, H., Ma, X., & Li, Z. (2021). A deep learning model for small-size defective components detection in power transmission tower. IEEE Transactions on Power Delivery, 37(4), 2551-2561. Retrieved from https://ieeexplore.ieee.org/document/9537695
  14. Kılıç, K. (2025). A computer vision based machine learning approach for wood defect detection (Doctoral dissertation). Gazi University, Graduate School of Natural and Applied Sciences, Ankara, Turkey.
  15. Kirat, S. S., & Aydin, İ. (2023). Açıklanabilir Yapay Zekâ Tabanlı Denetimsiz Öğrenme ile Ray Kusur Tespiti. Demiryolu Mühendisliği(18), 1-13. Doi: https://doi.org/10.47072/demiryolu.1231751
  16. Koç, Y. (2022). Hasarlı güneş paneli hücrelerinin derin öğrenme yöntemleriyle sınıflandırılması [Classification of damaged solar panel cells using deep learning methods] (Master's thesis). Amasya University, Amasya, Turkey.
  17. Li, Y., Huang, H., Xie, Q., Yao, L., & Chen, Q. (2018). Research on a surface defect detection algorithm based on MobileNet-SSD. Applied Sciences, 8(9), 1678. Doi: https://doi.org/10.3390/app8091678
  18. Li, Z., Liu, X., Wen, S., He, P., Zhong, K., Wei, Q., … Liu, S. (2018). In situ 3D monitoring of geometric signatures in the powder-bed-fusion additive manufacturing process via vision sensing methods. Sensors, 18(4), 1180. Doi: https://doi.org/10.3390/s18041180
  19. Lopes, J. F., Ludwig, L., Barbin, D. F., Grossmann, M. V. E., & Barbon, S., Jr. (2019). Computer vision classification of barley flour based on spatial pyramid partition ensemble. Sensors, 19(13), 2953. Doi: https://doi.org/10.3390/s19132953
  20. Meral, Y. E. (2024). Görüntü işleme ile desenlerde kusur tespiti [Defect detection in patterns with image processing] (Master's thesis). İzmir Kâtip Çelebi University, İzmir, Turkey.
  21. Metlek, S., & Çetiner, H. (2024). Inception Sh: A New Cnn Model Based on Inception Module for Classifying Scene Images. Mühendislik Bilimleri ve Tasarım Dergisi, 12(2), 328-344. Doi: https://doi.org/10.21923/jesd.1372788
  22. Ozcan, S., & Sengul, U. (2025). The use of supervised artificial intelligence methods in quality determination in continuous production lines: A case study of ceramic industry. International Journal on Interactive Design and Manufacturing (IJIDeM), 19(12), 8687-8706. Doi: https://doi.org/10.1007/s12008-025-02310-w
  23. Pirim, A. G. H. (2006). Yapay zeka. Yaşar Üniversitesi E-Dergisi, 1(1), 81-93.
  24. Prusty, S., Dash, S. K., & Patnaik, S. (2022). A novel transfer learning technique for detecting breast cancer mammograms using VGG16 bottleneck feature. ECS Transactions, 107(1), 733-746. Retrieved from https://iopscience.iop.org/article/10.1149/10701.0733ecst/meta
  25. Rebhi, A., Benmhammed, I., Abid, S., & Fnaiech, F. (2015). Fabric Defect Detection Using Local Homogeneity Analysis and Neural Network. Journal of Photonics, 2015, 1-9. Doi: https://doi.org/10.1155/2015/376163
  26. Saberironaghi, A. (2023). Deep learning models for defect and anomaly detection on industrial surfaces (Master's thesis). Ontario Tech University, Oshawa, Ontario, Canada. Retrieved from https://ontariotechu.scholaris.ca/items/af692a29-1113-40c8-905e-8472ae3b656a
  27. Saedi, S. I., & Rezaei, M. (2023). A modified xception deep learning model for automatic sorting of olives based on ripening stages. Inventions, 9(1), 6. Doi: https://doi.org/10.3390/inventions9010006
  28. Senthilkumar, C., & Kamarasan, M. (2021). An effective citrus disease detection and classification using deep learning based inception resnet V2 model. Turkish Journal of Computer and Mathematics Education, 12(12), 2283-2296.
  29. Sunal, S. (2022). Yapay Zeka, Büyük Veri ve Otomasyon: Mevcut Durum, Beklentiler ve Olanaklar. Madde Diyalektik ve Toplum, 5(2), 147-155.
  30. Swaminathan, A., Varun, C., & Kalaivani, S. (2021). Multiple plant leaf disease classification using densenet-121 architecture. Int. J. Electr. Eng. Technol, 12(5), 38-57.
  31. Tan, M., & Emeksiz, C. (2023). Yüz Tanıma Sistemleri İçin Geliştirilmiş Veri Artırma Temelli Adaptif Yüz Tanıma Modeli. Düzce Üniversitesi Bilim ve Teknoloji Dergisi, 11(2), 588-606. Doi: https://doi.org/10.29130/dubited.1024670
  32. Üzen, H., Türkoğlu, M., Ari, A., & Hanbay, D. (2022). Piksel seviyesinde yüzey hata tespiti için InceptionV3 tabanlı zenginleştirilmiş öznitelik entegrasyon ağ mimarisi. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, 38(2), 721-732. Doi: https://doi.org/10.17341/gazimmfd.1024425
  33. Vásquez Lobos, J. M. (2022). Machine learning for zero defect manufacturing (Diploma thesis). Technische Universität Wien, Vienna, Austria. https://doi.org/10.34726/hss.2022.95242
  34. Yıldırım, Y. (2025). Hava alanları kaplamalı sahalarında oluşan yüzey kusurlarının derin öğrenme ile tespit edilmesi [Detection of surface defects on airport paved areas using deep learning] (Master's thesis). Atatürk University, Erzurum, Turkey.
  35. Zhao, S., Yin, L., Zhang, J., Wang, J., & Zhong, R. (2020). Real‐time fabric defect detection based on multi‐scale convolutional neural network. IET Collaborative Intelligent Manufacturing, 2(4), 189-196. Doi: https://doi.org/10.1049/iet-cim.2020.0062
  36. Zhong, X., Zhu, J., Liu, W., Hu, C., Deng, Y., & Wu, Z. (2023). An Overview of Image Generation of Industrial Surface Defects. Sensors (Basel), 23(19). Doi: https://doi.org/10.3390/s23198160
  37. Ali, A., Shahbaz, H., & Damaševičius, R. (2025). xCViT: Improved Vision Transformer Network with Fusion of CNN and Xception for Skin Disease Recognition with Explainable AI. Computers, Materials & Continua, 83(1), 1367-1398. Doi: https://doi.org/10.32604/cmc.2025.059301
  38. Alom, M. Z., Hasan, M., Yakopcic, C., Taha, T. M., & Asari, V. K. (2020). Improved inception-residual convolutional neural network for object recognition. Neural Computing and Applications, 32(1), 279-293. Doi: https://doi.org/10.1007/s00521-018-3627-6
  39. Diogo, A. R., Moreira, B., Gouveia, C. A., & Tavares, J. M. R. (2022). A review of signal processing techniques for ultrasonic guided wave testing. Metals, 12(6), 936. Doi: https://doi.org/10.3390/met12060936
  40. Ferguson, M. K., Ronay, A., Lee, Y. T., & Law, K. H. (2018). Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learning. Smart Sustain Manuf Syst, 2. Doi: https://doi.org/10.1520/SSMS20180033
  41. Hossain, A. A., Nisha, J. K., & Johora, F. (2023). Breast cancer classification from ultrasound images using transfer learning based on VGG16 model. International Journal of Image, Graphics and Signal Processing, 15(1), 12-22. Doi: https://doi.org/10.5815/ijigsp.2023.01.02
  42. Kirat, S. S., & Aydin, İ. (2023). Açıklanabilir Yapay Zekâ Tabanlı Denetimsiz Öğrenme ile Ray Kusur Tespiti. Demiryolu Mühendisliği(18), 1-13. Doi: https://doi.org/10.47072/demiryolu.1231751
  43. Li, Y., Huang, H., Xie, Q., Yao, L., & Chen, Q. (2018). Research on a surface defect detection algorithm based on MobileNet-SSD. Applied Sciences, 8(9), 1678. Doi: https://doi.org/10.3390/app8091678
  44. Li, Z., Liu, X., Wen, S., He, P., Zhong, K., Wei, Q., … Liu, S. (2018). In situ 3D monitoring of geometric signatures in the powder-bed-fusion additive manufacturing process via vision sensing methods. Sensors, 18(4), 1180. Doi: https://doi.org/10.3390/s18041180
  45. Lopes, J. F., Ludwig, L., Barbin, D. F., Grossmann, M. V. E., & Barbon, S., Jr. (2019). Computer vision classification of barley flour based on spatial pyramid partition ensemble. Sensors, 19(13), 2953. Doi: https://doi.org/10.3390/s19132953
  46. Metlek, S., & Çetiner, H. (2024). Inception Sh: A New Cnn Model Based on Inception Module for Classifying Scene Images. Mühendislik Bilimleri ve Tasarım Dergisi, 12(2), 328-344. Doi: https://doi.org/10.21923/jesd.1372788
  47. Ozcan, S., & Sengul, U. (2025). The use of supervised artificial intelligence methods in quality determination in continuous production lines: A case study of ceramic industry. International Journal on Interactive Design and Manufacturing (IJIDeM), 19(12), 8687-8706. Doi: https://doi.org/10.1007/s12008-025-02310-w
  48. Rebhi, A., Benmhammed, I., Abid, S., & Fnaiech, F. (2015). Fabric Defect Detection Using Local Homogeneity Analysis and Neural Network. Journal of Photonics, 2015, 1-9. Doi: https://doi.org/10.1155/2015/376163
  49. Saedi, S. I., & Rezaei, M. (2023). A modified xception deep learning model for automatic sorting of olives based on ripening stages. Inventions, 9(1), 6. Doi: https://doi.org/10.3390/inventions9010006
  50. Tan, M., & Emeksiz, C. (2023). Yüz Tanıma Sistemleri İçin Geliştirilmiş Veri Artırma Temelli Adaptif Yüz Tanıma Modeli. Düzce Üniversitesi Bilim ve Teknoloji Dergisi, 11(2), 588-606. Doi: https://doi.org/10.29130/dubited.1024670
  51. Üzen, H., Türkoğlu, M., Ari, A., & Hanbay, D. (2022). Piksel seviyesinde yüzey hata tespiti için InceptionV3 tabanlı zenginleştirilmiş öznitelik entegrasyon ağ mimarisi. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, 38(2), 721-732. Doi: https://doi.org/10.17341/gazimmfd.1024425
  52. Zhao, S., Yin, L., Zhang, J., Wang, J., & Zhong, R. (2020). Real‐time fabric defect detection based on multi‐scale convolutional neural network. IET Collaborative Intelligent Manufacturing, 2(4), 189-196. Doi: https://doi.org/10.1049/iet-cim.2020.0062
  53. Zhong, X., Zhu, J., Liu, W., Hu, C., Deng, Y., & Wu, Z. (2023). An Overview of Image Generation of Industrial Surface Defects. Sensors (Basel), 23(19). Doi: https://doi.org/10.3390/s23198160