Kalite Kontrol Uygulamalarında Yapay Görme Sistemleri mi Yoksa İnsan Değerlendirmesi mi Daha Avantajlıdır?

Öz

Kalite ölçümü, ürünlerin belirli bir standarda uygunluğunu değerlendirmek için kullanılan bir süreçtir. Bu sürecin yapılmasında hem yapay görme sistemleri (bilgisayarlı görme, görüntü işleme gibi) hem de insanlar kullanılabilir. Yapay görme sistemleri, özellikle büyük veri setlerini hızla analiz edebilme yetenekleri sayesinde yüksek verimlilik sağlayabilir. Tekrarlanabilir sonuçlar elde etme konusunda insan faktörü dezavantajlı olduğu için nesnel sonuçlar elde edilebilir. Ancak, yapay görme sistemlerinin eğitimi ve kalibrasyonu gereklidir, bu da zaman ve kaynak gerektirir. İnsanlar ise deneyim ve uzmanlık sahibi oldukları durumlarda özellikle karmaşık veya öznel değerlendirmelerde daha üstün olabilirler. Özellikle sanatsal veya estetik değerlendirmeler gibi konularda insan görüşü daha değerli olabilir. Yapay görme sistemleri ön işleme ve hızlı analiz sağlarken, insanlar öznel veya karmaşık değerlendirmelerde son kararı verebilirler. Hangi yöntemin kullanılacağına karar verirken, ölçümün doğası, karmaşıklığı ve gereksinimler göz önünde bulundurulmalıdır.

Anahtar Kelimeler

• Kalite Kontrol
• Yapay Görme Sistemleri
• İnsan Kontrolü

Are Machine Vision Systems or Human Evaluation More Advantageous in Quality Control Applications?

Abstract

Quality measurement is a process used to evaluate the conformity of products to a certain standard. Both machine vision systems (such as computer vision, image processing) and humans can be used to perform this process. Machine vision systems can provide high efficiency, especially thanks to their ability to quickly analyze large data sets. Objective results can be obtained because the human factor is at a disadvantage in obtaining reproducible results. However, training and calibration of machine vision systems is necessary, which takes time and resources. People, on the other hand, may be superior when they have experience and expertise, especially in complex or subjective evaluations. Human opinion may be more valuable, especially in matters such as artistic or aesthetic evaluations. Humans can make the final decision on subjective or complex evaluations, while machine vision systems provide pre-processing and rapid analysis. When deciding which method to use, the nature of the measurement, complexity, and requirements should be considered.

Keywords

• Quality Control
• Machine Vision Systems
• Human Control

Kaynakça

1. Abagiu, M., Cojocaru, D., Manta, L., ve Mariniuc, A. (2023). Detecting Machining Defects İnside Engine Piston Chamber With Computer Vision And Machine Learning. Sensors, 23(2), 785. https://doi.org/10.3390/s23020785
2. Akyurt, İ. (2020). Gıda Sektöründe Istatistiksel Proses Kontrolü: Endüstriyel Ekmek Üretim Tesisi Uygulaması. Erzincan Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 13(1), 235-257. https://doi.org/10.18185/erzifbed.605670
3. Arsalan, M., ve Aziz, A. (2012). Low-cost Machine Vision System for Dimension Measurement of Fast Moving Conveyor Products. International Conference on Open-Source Systems s.22-27. 10.1109/ICOSST.2012.6472822.
4. Ataş, M., ve Doğan, Y. (2015). Classification of Closed and Open Shell Pistachio Nuts by Machine Vision. International Conference on Advanced Technology Sciences, Antalya.
5. Banus, N., Boada, I., Xiberta, P., Toldra, P., ve Bustins, N. (2021). Deep Learning For The Quality Control Of Thermoforming Food Packages. Scientific Reports, 11(1). https://doi.org/10.1038/s41598-021-01254-x
6. Boukherouaa, E. B., AlAjmi, K., Deodoro, J., Farias, A., ve Ravikumar, R. (2021). Powering the Digital Economy: Opportunities and Risks of Artificial Intelligence in Finance, Departmental Papers, 2021(024), A001. https://doi.org/10.5089/9781589063952.087.A001
7. Çelik, A. ve Tekin, E. (2020). Tekstil Baskı Kalite Kontrolünün Görüntü İşleme Teknikleri Ile Gerçekleştirilmesi. European Journal of Science and Technology, 268-276. https://doi.org/10.31590/ejosat.araconf34
8. Deepak, J. R., Raja, V., Srikanth, D., Surendran, H., ve Nickolas, M. M. (2021). Non-Destructive Testing (NDT) Techniques for Low Carbon Steel Welded Joints: A Review and Experimental Study. Materials Today: Proceedings. s.3732-3737. 44. 10.1016/J.Matpr.2020.11.578.

9. Elmesiry, H., Mao, H., ve Abomohra, A. (2019). Applications of Non-destructive Technologies for Agricultural and Food Products Quality Inspection. Sensors. 19. 846. s.1-23 10.3390/s19040846.
10. Fang, X., Luo, Q., Zhou, B., Li, C., ve Tian, L. (2020). Research Progress Of Automated Visual Surface Defect Detection For Industrial Metal Planar Materials. Sensors, 20(18), 5136. https://doi.org/10.3390/s20185136
11. Gupta, M., Khan, M., Butola, R., ve Singari, R. (2021). Advances in Applications of Non-Destructive Testing (NDT): A Review. Advances In Materials and Processing Technologies. 8. s.1-22. 10.1080/2374068X.2021.1909332.
12. Hosny, A., Parmar, C., Quackenbush, J., Schwartz, L.H. ve Aerts H.J.W.L. (2018). Artificial Intelligence in Radiology. Nat Rev Cancer. s.1-27. doi: 10.1038/s41568-018-0016-5. PMID: 29777175; PMCID: PMC6268174.
13. Hosseinpour, S., Ilkhchi, H. A., ve Aghbashlo, M. (2018). An İntelligent Machine Vision-Based Smartphone App for Beef Quality Evaluation. Journal Of Food Engineering. s.9-22. 248. 10.1016/J.Jfoodeng.2018.12.009.
14. https://www.baslerweb.com/, (Erişim Tarihi: 12.05.2023).
15. https://instrumental.com/build-better-handbook/machine-vision-vs-manual-inspection-vs-instrumental, (Erişim Tarihi: 04.01.2024).
16. https://www.roboticstomorrow.com/, (Erişim Tarihi: 13.08.2023).
17. Işık, S. ve Kara, P. (2020). Nükleer Tıpta Gama Kameraların Günlük Çalışma Verimini Belirlemede Kalite Kontrollerin Önemi: Paratiroid Sintigrafisi Spect Çalışması Esnasında Gözlenen Fotoçoğaltıcı Tüp Defekti Vakası. Acıbadem Universitesi Sağlık Bilimleri Dergisi, 0-0. https://doi.org/10.31067/0.2019.158
18. Javaid, M., Haleem, A., Singh, R.P., Rab, S., ve Suman, R. (2022). Exploring Impact and Features of Machine Vision for Progressive Industry 4.0 Culture. Sensors Int, s.1-11 Article 100132, 10.1016/j.sintl.2021.100132
19. Khalighy, S., Green, G., Scheepers, C., ve Whittet, C. (2015). Quantifying the Qualities of Aesthetics İn Product Design Using Eye-Tracking Technology. International Journal of Industrial Ergonomics. 49. s.31-43. 10.1016/J.Ergon.2015.05.011.
20. Khogali, H. O., ve Mekid, S. (2023). The Blended Future of Automation And AI: Examining Some Long-Term Societal and Ethical Impact Features. Technology in Society. s.1-10
21. Koçak, A. T. (2006). Globalleşme Sürecinde İnsan Kaynakları Yönetiminde Değişimler. İstanbul Üniversitesi. Sosyal Bilimler Enstitüsü. İstanbul. Yüksek Lisans Tezi
22. Kumar, R., Patil, O., Nath, K., Sangwan, K., ve Kumar., R. (2021), A Machine Vision-based Cyber-Physical Production System for Energy Efficiency and Enhanced Teaching-Learning Using a Learning Factory. Procedia CIRP. 98. s.424-429. 10.1016/j.procir.2021.01.128.
23. Kumar, P., Singh, D., ve Bhamu, J. (2022). Machine Vision in Industry 4.0. CRC Press 10.1201/9781003122401-13.
24. Labudzki, R., Legutko, S., ve Raos, P. (2014). The Essence and Applications of Machine Vision. Tehnicki Vjesnik. 21. s.903-909.
25. Mavridou, E., Vrochidou, E., Papakostas, G.A., Pachidis, T., ve Kaburlasos, V. G. (2019). Machine Vision Systems in Precision Agriculture for Crop Farming. Journal of Imaging.; 5(12):89. s.1-32. https://doi.org/10.3390 /jimaging5120089
26. Patel, K., Kar, A., Jha, S., ve Khan, M. (2012). Machine Vision System: A Tool for Quality İnspection Of Food And Agricultural Products. Journal Of Food Science and Technology. 49. s.123-141. 10.1007/S13197-011-0321-4.
27. Park, M., ve Jeong, J. (2022). Design and Implementation of Machine Vision-Based Quality Inspection System in Mask Manufacturing Process. Sustainability. 14. 6009. 10.3390/su14106009.
28. Ren, Z., Fang, F., ve Yan, N. (2022). State of the Art in Defect Detection Based on Machine Vision. Int. J. of Precis. Eng. and Manuf.-Green Tech. 9, s.661–691. https://doi.org/10.1007/s40684-021-00343-6.
29. Sarker, I. H. (2021), Machine Learning: Algorithms, Real-World Applications and Research Directions. SN COMPUT. SCI. 2, 160. https://doi.org/10.1007/s42979-021-00592-x.
30. Shtembari, E., Kufo A., ve Haxhinasto, D. (2022). Employee Compensation and Benefits Pre and Post COVID-19. Administrative Sciences. 12(3):106. s.1-17. https://doi.org/10.3390/admsci12030106
31. Silva, M., Malitckii, E., Santos, T., ve Vilaça, P. (2023). Review of Conventional and Advanced Non-Destructive Testing Techniques for Detection and Characterization of Small-Scale Defects. Progress İn Materials Science. 138. s.1-69. 101155. 10.1016/J.Pmatsci.2023.101155.
32. Sun, T., ve Cao, J. (2022). Research on Machine Vision System Design Based on Deep Learning Neural Network. Wireless Communications and Mobile Computing. s.1-16. 10.1155/2022/4808652.
33. Toner, P. (2011), Workforce Skills and Innovation: An Overview of Major Themes In The Literature. OECD Publications.
34. Vahab, A., Naik, M. S., Raikar, P. G., ve Prasad, S. R. (2019). Applications of Object Detection System. International Research Journal of Engineering and Technology (IRJET), 6(4), s.4186-4192.
35. Van der Stuyft, E., Schofield, C. P., Randall, J. M., Wambacq, P., ve Goedseels, V. (1991). Development and Application of Computer Vision Systems for Use in Livestock Production. Computers and Electronics in Agriculture, 6(3), s.243-265.
36. Venkateshaiah, A., Padil, V., Nagalakshmaiah, M., Wacławek, S., Cerník, M., ve Varma, Rajender. (2020), Microscopic Techniques for the Analysis of Micro and Nanostructures of Biopolymers and Their Derivatives. Polymers. 12. s.1-33 10.3390/polym12030512.
37. Walters, K., ve Rodriguez, J. (2017). The Importance of Training and Development in Employee Performance and Evaluation. World Wide Journal of Multidisciplinary Research and Development. s.206-2012 e-ISSN: 2454-6615.
38. Yalçın, H. (2016). Computer Vision Based Characterization Of Production Phases For Pastry Goods. https://doi.org/10.1109/siu.2016.7495891
39. Zhu, L., Spachos, P., Pensini, E., ve Plataniotis, K. (2021). Deep Learning and Machine Vision for Food Processing: A Survey. Current Research In Food Science. 4. s.233-249. 10.1016/J.Crfs.2021.03.009.