FARKLI YÜZEY TÜRLERİNE SAHİP ÜRÜNLERİN HATA TESPİTİNDE EVRİŞİMSEL SİNİR AĞI MİMARİLERİNİN ETKİSİ

Betül Karakaş; Sinem Kulluk

doi:10.17780/ksujes.1640228

TR EN

FARKLI YÜZEY TÜRLERİNE SAHİP ÜRÜNLERİN HATA TESPİTİNDE EVRİŞİMSEL SİNİR AĞI MİMARİLERİNİN ETKİSİ

Öz

Üretim sistemlerinde üretilen ürünlerin hatalarının hızlı ve doğru bir şekilde tespit edilmesi maliyet, kalite ve müşteri memnuniyeti açısından önem teşkil etmektedir. Ürün yüzey hataları üretim hatalarının büyük bir kısmını kapsamaktadır. Yüzey hatalarının tespiti derin öğrenme yöntemleri ile başarılı bir şekilde gerçekleştirilebilmektedir. Bu çalışmada derin öğrenme yöntemlerinden Evrişimsel Sinir Ağı mimarileri kullanılmıştır. Farklı türdeki yüzey hataları üzerinde sınıflandırma işlemi gerçekleştirerek, değişen endüstriyel süreçlere uyum sağlamayı kolaylaştırmak ve farklı mimarilerin farklı yüzey türleri üzerindeki etkilerinin incelenmesi amaçlanmıştır. Metal, Ahşap, Gıda ve Kumaş türlerine sahip dört veri kümesi GoogleNet, SqueezeNet ve VGG 19 olmak üzere üç farklı CNN mimarisi ile sınıflandırılmış, başarıları incelenmiştir. Sınıflandırma işleminde validasyon doğruluk değeri göz önünde bulundurulmuştur. Elde edilen sonuçlara göre siyah-beyaz tonlamaya sahip Metal ve Kumaş veri kümelerinde GoogleNet mimarisi sırasıyla %99,89 ve %96,86 ile diğer mimarilerden daha yüksek sınıflandırma başarısı ortaya koyarken, renkli tonlamaya sahip veri kümeleri olan Ahşap ve Gıda veri kümelerinde VGG 19 mimarisi sırasıyla %94,39 ve %99,96 ile daha yüksek sınıflandırma başarısı göstermiştir. Yapılan çalışma sonucunda Ahşap ve Kumaş veri kümeleri için elde edilen sınıflandırma başarıları literatürdeki çalışmalara göre ortalamanın üzerinde elde edilirken, Metal ve Gıda veri kümeleri için sınıflandırma başarıları literatürdeki çalışmalardan daha yüksek olarak elde edilmiştir.

Anahtar Kelimeler

EFFECT OF CONVOLUTIONAL NEURAL NETWORK ARCHITECTURES ON DEFECT DETECTION OF PRODUCTS WITH DIFFERENT SURFACE TYPES

Abstract

Fast and accurate detection of product defects in manufacturing systems is crucial for cost, quality and customer satisfaction. Surface defects comprise a large portion of production defects and can be successfully detected using deep learning methods. This study employed Convolutional Neural Network (CNN) architectures to classify different types of surface defects and examine the effects of different architectures on various surface types. Four datasets (Metal, Wood, Food, and Fabric) were classified using three CNN architectures: GoogleNet, SqueezeNet, and VGG 19. Validation accuracy was considered in the classification process. According to the results, for the grayscale Metal and Fabric datasets, the GoogleNet architecture achieved higher classification accuracies than the other architectures, with 99,89% and 96,86%, respectively. In contrast, for the color datasets, namely Wood and Food, the VGG19 architecture demonstrated higher classification performance, achieving 94,39% and 99,96%, respectively. As a result of this study, the classification accuracies obtained for the Wood and Fabric datasets were above the average reported in the literature, while the accuracies for the Metal and Food datasets surpassed those reported in previous studies.

Keywords

References

Abbes, W., Elleuch, J. F., & Sellami, D. (2024). Defect-Net: A new CNN model for steel surface defect classification. Paper presented at the 2024 IEEE 12th International Symposium on Signal, Image, Video and Communications (ISIVC), https://doi.org/10.1109/ISIVC61350.2024.10577945
Ahuja, S. K., & Shukla, M. K. (2018). A survey of computer vision based corrosion detection approaches. Information and Communication Technology for Intelligent Systems (ICTIS 2017)-Volume 2 2, 55-63. https://doi.org/10.1007/978-3-319-63645-0_6
Amin, U., Shahzad, M. I., Shahzad, A., Shahzad, M., Khan, U., & Mahmood, Z. (2023). Automatic fruits freshness classification using CNN and transfer learning. Applied Sciences, 13(14), 8087. https://doi.org/10.3390/app13148087
Anvar, A., & Cho, Y. I. (2020). Automatic metallic surface defect detection using shuffledefectnet. Journal of The Korea Society of Computer and Information, 25(3), 19-26.
Ashrafi, S., Teymouri, S., Etaati, S., Khoramdel, J., Borhani, Y., & Najafi, E. (2025). Steel surface defect detection and segmentation using deep neural networks. Results in Engineering, 25, 103972. https://doi.org/10.1016/j.rineng.2025.103972
Austin, M., Delgoshaei, P., Coelho, M., & Heidarinejad, M. (2020). Architecting smart city digital twins: Combined semantic model and machine learning approach. Journal of Management in Engineering, 36(4), 04020026. https://doi.org/10.1061/(ASCE)ME.1943-5479.0000774
Beljadid, A., Tannouche, A., & Balouki, A. (2023). Fabric defect classification using transfer learning and deep learning. IAES International Journal of Artificial Intelligence (IJ-AI), 2252(8938), 1379. https://doi.org/10.11591/ijai.v12.i3.pp1378-1385
Bengio, Y. (2009). Learning Deep Architectures for AI. Foundations and trends in Machine Learning, 2(1), 1-127. http://dx.doi.org/10.1561/2200000006

Calvi, A. (2020). Wood Classifier - Version 0.1a of the 10/09/2020. https://github.com/ArthurCalvi/Classifieur-Bois (Erişim Tarihi: 2024, Aralık)
Cao, W., Liu, Q., & He, Z. (2020). Review of pavement defect detection methods. Ieee Access, 8, 14531-14544. https://doi.org/10.1109/ACCESS.2020.2966881
Chen, Z., Huang, X., Kang, R., Huang, J., & Peng, J. (2025). Aluminum Product Surface Defect Detection Method Based on Improved CenterNet. IEEJ Transactions on Electrical and Electronic Engineering, 20(3), 415-421. https://doi.org/10.1002/tee.24218
Czimmermann, T., Ciuti, G., Milazzo, M., Chiurazzi, M., Roccella, S., Oddo, C. M., & Dario, P. (2020). Visual-based defect detection and classification approaches for industrial applications—a survey. Sensors, 20(5), 1459. https://doi.org/10.3390/s20051459
Dabhi, R. (2020). Casting Product Image Data for Quality Inspection. https://www.kaggle.com/datasets/ravirajsinh45/real-life-industrial-dataset-of-casting-product/data (Erişim Tarihi: 2024, Aralık)
Fouzia, M., & Nirmala, K. (2010). A literature survey on various methods used for metal defects detection using image segmentation. Evaluation, 5(10), 8.
Fu, G., Le, W., Zhang, Z., Li, J., Zhu, Q., Niu, F., . . . Shen, Y. (2023). A surface defect inspection model via rich feature extraction and residual-based progressive integration CNN. Machines, 11(1), 124. https://doi.org/10.3390/machines11010124
Habibpour, M., Gharoun, H., Tajally, A., Shamsi, A., Asgharnezhad, H., Khosravi, A., & Nahavandi, S. (2021). An uncertainty-aware deep learning framework for defect detection in casting products. arXiv preprint arXiv:2107.11643. https://doi.org/10.48550/arXiv.2107.11643
Hafemann, L. G., Oliveira, L. S., & Cavalin, P. (2014). Forest species recognition using deep convolutional neural networks. Paper presented at the 2014 22nd international conference on pattern recognition, https://doi.org/10.1109/ICPR.2014.199
Hoang, D.-T., & Kang, H.-J. (2019). A survey on deep learning based bearing fault diagnosis. Neurocomputing, 335, 327-335. https://doi.org/10.1016/j.neucom.2018.06.078
Hu, B., & Wang, J. (2020). Detection of PCB surface defects with improved faster-RCNN and feature pyramid network. Ieee Access, 8, 108335-108345.
Iandola, F. N., Han, S., Moskewicz, M. W., Ashraf, K., Dally, W. J., & Keutzer, K. (2016). SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size. arXiv preprint arXiv:1602.07360. https://doi.org/10.48550/arXiv.1602.07360
Jing, J. F., Ma, H., & Zhang, H. H. (2019). Automatic fabric defect detection using a deep convolutional neural network. Coloration Technology, 135(3), 213-223. https://doi.org/10.1111/cote.12394
Kalluri, S. R. (2018). Fresh and Rotten Fruits for Classification. https://www.kaggle.com/datasets/sriramr/fruits-fresh-and-rotten-for-classification (Erişim Tarihi: 2024, Kasım)
Kumar, A. (2008). Computer-vision-based fabric defect detection: A survey. IEEE transactions on industrial electronics, 55(1), 348-363. https://doi.org/10.1109/TIE.1930.896476
Lee, D., Kang, Y.-i., Park, C., & Won, S. (2009). Defect detection algorithm in steel billets using morphological top-hat filter. IFAC Proceedings Volumes, 42(23), 209-212. https://doi.org/10.3182/20091014-3-CL-4011.00038
Li, S., Yang, J., Wang, Z., Zhu, S., & Yang, G. (2020). Review of development and application of defect detection technology. Acta Automatica Sinica, 46(11), 2319-2336.
Liang, Q., Zhu, W., Sun, W., Yu, Z., Wang, Y., & Zhang, D. (2019). In-line inspection solution for codes on complex backgrounds for the plastic container industry. Measurement, 148, 106965. https://doi.org/10.1016/j.measurement.2019.106965
Liu, Y., Xu, K., & Xu, J. (2019). An improved MB-LBP defect recognition approach for the surface of steel plates. Applied Sciences, 9(20), 4222. https://doi.org/10.3390/app9204222
Masters, D., & Luschi, C. (2018). Revisiting small batch training for deep neural networks. arXiv preprint arXiv:1804.07612. https://doi.org/10.48550/arXiv.1804.07612
Park, J.-K., Kwon, B.-K., Park, J.-H., & Kang, D.-J. (2016). Machine learning-based imaging system for surface defect inspection. International Journal of Precision Engineering and Manufacturing-Green Technology, 3, 303-310. https://doi.org/10.1007/s40684-016-0039-x
Parlak, I. E., & Emel, E. (2023). Deep learning-based detection of aluminum casting defects and their types. Engineering Applications of Artificial Intelligence, 118, 105636. https://doi.org/10.1016/j.engappai.2022.105636
Pathak, R., & Makwana, H. (2021). Classification of fruits using convolutional neural network and transfer learning models. Journal of Management Information and Decision Sciences, 24, 1-12.
Putri, A. P., Rachmat, H., & Atmaja, D. S. E. (2017). Design of automation system for ceramic surface quality control using fuzzy logic method at Balai Besar Keramik (BBK). Paper presented at the MATEC Web of Conferences, https://doi.org/10.1051/matecconf/201713500053
Rasheed, A., Zafar, B., Rasheed, A., Ali, N., Sajid, M., Dar, S. H., . . . Mahmood, M. T. (2020). Fabric defect detection using computer vision techniques: a comprehensive review. Mathematical Problems in Engineering, 2020(1), 8189403. https://doi.org/10.1155/2020/8189403
Ren, Z. (2024). Surface Defect Detection and Classification Methods for Aluminum Profiles Based on CNN. Paper presented at the 2024 17th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), https://doi.org/10.1109/CISP-BMEI64163.2024.10906210
Schulz-Mirbach, H. (1996). Tilda-ein referenzdatensatz zur evaluierung von sichtprüfungsverfahren für textiloberflächen. Interner Bericht, 4, 96.
Shilong, M., Qiqige, W., & Xiaoping, L. (2016). Deep learning with big data: state of the art and development. CAAI Transaction on Intelligent Systems, 11, 728-742.
Simonyan, K., & Zisserman, A. (2014). Very deep convnets for large-scale image recognition. Computing Research Repository.
Smith, L. N., & Topin, N. (2019). Super-convergence: Very fast training of neural networks using large learning rates. Paper presented at the Artificial intelligence and machine learning for multi-domain operations applications, https://doi.org/10.1117/12.2520589
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., . . . Rabinovich, A. (2015). Going deeper with convolutions. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.
Tao, X., Hou, W., & Xu, D. (2021). A survey of surface defect detection methods based on deep learning. Acta Automatica Sinica, 47(5), 1017-1034.
Tao, X., Zhang, D., Wang, Z., Liu, X., Zhang, H., & Xu, D. (2018). Detection of power line insulator defects using aerial images analyzed with convolutional neural networks. IEEE transactions on systems, man, and cybernetics: systems, 50(4), 1486-1498. https://doi.org/10.1109/TSMC.2018.2871750
Tata, R. K., & KBV, B. R. (2025). Hybrid CNN-LSTM Architecture for Automated Defect Detection in Industrial Surface Inspection. MJARET, 5(1), 11-16.
Ünal, E., İnanç, H., & Nebati, E. E. (2024). Bir Ambalaj İşletmesinde SMED ve 5S Uygulaması. İşletme Bilimi Dergisi, 12(2), 196-214. https://doi.org/10.22139/jobs.1501171
Wang, T., Chen, Y., Qiao, M., & Snoussi, H. (2018). A fast and robust convolutional neural network-based defect detection model in product quality control. The International Journal of Advanced Manufacturing Technology, 94, 3465-3471. https://doi.org/10.1007/s00170-017-0882-0
Xu, L., Lv, S., Deng, Y., & Li, X. (2020). A weakly supervised surface defect detection based on convolutional neural network. Ieee Access, 8, 42285-42296. https://doi.org/10.1109/ACCESS.2020.2977821
Yang, J., Li, S., Wang, Z., Dong, H., Wang, J., & Tang, S. (2020). Using deep learning to detect defects in manufacturing: a comprehensive survey and current challenges. Materials, 13(24), 5755. https://doi.org/10.3390/ma13245755

Details

Primary Language

Turkish

Subjects

Deep Learning , Industrial Engineering

Journal Section

Research Article

Authors

Betül Karakaş ^*
0000-0001-5524-9864
Türkiye

Sinem Kulluk
0000-0002-0675-3113
Türkiye

Publication Date

December 3, 2025

Submission Date

February 17, 2025

Acceptance Date

September 12, 2025

Published in Issue

Year 2025 Volume: 28 Number: 4

DOI

https://doi.org/10.17780/ksujes.1640228

IZ

https://izlik.org/JA63TF92JZ

Cite

RIS / Bibtex

APA

Karakaş, B., & Kulluk, S. (2025). FARKLI YÜZEY TÜRLERİNE SAHİP ÜRÜNLERİN HATA TESPİTİNDE EVRİŞİMSEL SİNİR AĞI MİMARİLERİNİN ETKİSİ. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 28(4), 1673-1687. https://doi.org/10.17780/ksujes.1640228