Performance of deep learning approaches for detection and classification of ceramic tile defects
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Ceramic tiles are in high demand in the infrastructure and building development industries due to their low cost, ease ofinstallation, maintenance, moisture resistance, and availability in a broad range of colors, textures, and sizes. Automatedfacilities, which produce hundreds of tiles in every segment, require a tremendous volume of output. Because of the largenumber of tiles produced and the frequency with which they are produced, it is impossible to manually examine them forfaults, necessitating the use of a rapid, efficient, and reliable automated process. However, while the process of detecting flawsand categorizing them (or classification) is not as efficient as it might be, recent advances in computing technology,mathematical modeling, and high-resolution picture capture equipment have given rise to new prospects in the subject. Manykinds of literature on using these systems for the same goal are currently accessible. Deep learning is a type of artificialintelligence that helps people makes decisions. In production applications, image detection of faulty Ceramic Tile Surfaces isa critical skill. Deep learning is now being studied for its potential application in automated defect identification. As a result,we propose Deep Learning approaches that take advantage of the transform domain properties of the tiles image. The model'scapacity to learn via the system makes it versatile and dynamically customizable. Different deep learning-based fault detectionand classification transfer learning approaches are examined in this study.
Abstract
Ceramic tiles are in high demand in the infrastructure and building development industries due to their low cost, ease ofinstallation, maintenance, moisture resistance, and availability in a broad range of colors, textures, and sizes. Automatedfacilities, which produce hundreds of tiles in every segment, require a tremendous volume of output. Because of the largenumber of tiles produced and the frequency with which they are produced, it is impossible to manually examine them forfaults, necessitating the use of a rapid, efficient, and reliable automated process. However, while the process of detecting flawsand categorizing them (or classification) is not as efficient as it might be, recent advances in computing technology,mathematical modeling, and high-resolution picture capture equipment have given rise to new prospects in the subject. Manykinds of literature on using these systems for the same goal are currently accessible. Deep learning is a type of artificialintelligence that helps people makes decisions. In production applications, image detection of faulty Ceramic Tile Surfaces isa critical skill. Deep learning is now being studied for its potential application in automated defect identification. As a result,we propose Deep Learning approaches that take advantage of the transform domain properties of the tiles image. The model'scapacity to learn via the system makes it versatile and dynamically customizable. Different deep learning-based fault detectionand classification transfer learning approaches are examined in this study.
참고문헌 (27)
- L. J. Fiol, , J. Busin. Amp. Indust, 26(2), pp.132~145 (2011)
- S. Singh, , IOSR J. Eng, 2(3), pp.429~432 (2012)
- R. Mishra, , InInternati, 2(2), pp.1307~1322 (2012)
- D. S. Atmaja, , Jurn. Siste. Cerdas, 4(3), pp.171~179 (2021)
- A.P. Putri, , InMATEC Web of Conferences, pp.00053~ (2017)
- A. D. Septiani, , J. Titra, 1(1), pp.33~40 (2013)
- D.C. Montgomery, "Introduction to statistical quality control", pp.11~ (2020), John Wiley & Sons
- J. A. Yeow, , J. Appl. Scien, 14(24), pp.3464~3471 (2014)
- L.A. Martins, , Proceedings of InIECON 2010-36th Annual Conference, pp.1081~1086 (2010), IEEE
- R. Mishra, , Int. J. Emerg. Technol. Adv. Eng, 4(3), pp.229~233 (2014)
- H. Rachmat, , Proceedings of the 2nd International Conference on Soft Computing and Data Mining, pp.538~545 (2017), Springer International Publishing
- M. Sharma, , Int. J. Comput. Technol, 3(2), pp.259~262 (2012)
- T. C. Akinci, , Archives. Acoustics, 36(1), pp.77~85 (2011)
- X. Cheng, , Int. J. Eng and Manuf, 1(3), pp.1~ (2011)
- V. Mohan, , Int. J. Comp. Appli, 109(11), pp.24~27 (2015)
- S. Ramakrishnan, , Telecom. Sys, 46, pp.245~252 (2011)
- Y. Tao, , Proceedings 5th International Conference on Computational Intelligence and Multimedia Applications, pp.120~125 (2003), IEEE
- Y. Mingqiang, , Patt. Reco, 15(7), pp.43~90 (2008)
- R. M. Andrade, , J. Brazili. Society Mech. Sci. Eng, 33, pp.67~73 (2011)
- "A. Materka", 4968~ (1998)
- Z. Zhou, , Sensors, 19(22), pp.5000~ (2019)
- O. Stephen, , Electronics, 11(1), pp.55~ (2021)
- K. Wang, , Appli. Sci, 12(3), pp.1249~ (2022)
- Ayse Tunali, "Investigation of methods of reducing the number of pinhole defects in glossy-opaque floor tile glaze by modifying glaze properties", Journal of Ceramic Processing Research, 15(4), pp.225~230 (2014), 청정에너지연구소[DOI]
- Malek Ali, "A review on the effects of ceramic sand particles on most casting defects", Journal of Ceramic Processing Research, 23(3), pp.257~262 (2022), 청정에너지연구소[DOI]
- I. Tatar, , Beneficiation (2015)
- Sebastian Sado, "Use of Machine Learning for modelling the wear of MgO-C refractories in Basic Oxygen Furnace", Journal of Ceramic Processing Research, 23(4), pp.421~429 (2022), 청정에너지연구소[DOI]