Ceramic tile surface defect detection with integrated feature engineering and defect fuse classifier
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Introduction: Ceramic tile surface defect detection is crucial for ensuring product quality. This study proposes an integratedapproach combining feature engineering and a Defect Fuse Classifier for accurate defect detection. Methods: The proposedmodel utilizes Python and splits the collected data into 70% for training and 30% for testing. Purpose: The purposesection explicitly states the objectives of the study. It highlights the research goals, such as evaluating the effectiveness ofthe proposed methodology in detecting ceramic tile surface defects and exploring the impact of parameter variations ondetection performance. Results: Comparative analysis with state-of-the-art methods is conducted using various metrics suchas sensitivity, specificity, accuracy, precision, FPR, FNR, NPV, F-Measure, and MCC. (a) For a Training Rate of 70%: Theproposed Defect Fuse Classifier outperforms existing models with an accuracy of 97.4%, precision of 88.5%, sensitivity of88.5%, specificity of 98.5%, F-Measure of 88.5%, MCC of 87%, NPV of 98.5%, FPR of 1.4%, and FNR of 11.4%. Conclusion:This study introduces a novel deep learning approach for ceramic tile surface defect detection, encompassing data acquisition,pre-processing, feature extraction, feature selection, and deep learning-based defect detection. The proposed Defect FuseClassifier, integrating CNN, Bi-LSTM, and RNN, demonstrates superior performance, making it a promising solution fordefect detection in ceramic tile surfaces.
Abstract
Introduction: Ceramic tile surface defect detection is crucial for ensuring product quality. This study proposes an integratedapproach combining feature engineering and a Defect Fuse Classifier for accurate defect detection. Methods: The proposedmodel utilizes Python and splits the collected data into 70% for training and 30% for testing. Purpose: The purposesection explicitly states the objectives of the study. It highlights the research goals, such as evaluating the effectiveness ofthe proposed methodology in detecting ceramic tile surface defects and exploring the impact of parameter variations ondetection performance. Results: Comparative analysis with state-of-the-art methods is conducted using various metrics suchas sensitivity, specificity, accuracy, precision, FPR, FNR, NPV, F-Measure, and MCC. (a) For a Training Rate of 70%: Theproposed Defect Fuse Classifier outperforms existing models with an accuracy of 97.4%, precision of 88.5%, sensitivity of88.5%, specificity of 98.5%, F-Measure of 88.5%, MCC of 87%, NPV of 98.5%, FPR of 1.4%, and FNR of 11.4%. Conclusion:This study introduces a novel deep learning approach for ceramic tile surface defect detection, encompassing data acquisition,pre-processing, feature extraction, feature selection, and deep learning-based defect detection. The proposed Defect FuseClassifier, integrating CNN, Bi-LSTM, and RNN, demonstrates superior performance, making it a promising solution fordefect detection in ceramic tile surfaces.
참고문헌 (34)
- Q. Lu, , Adv. Eng. Inform, 53(8), pp.101692~ (2022)
- Y. Sun, , Int. J. Appl. Ceram. Technol, 19(1), pp.604~611 (2022)
- C. Wang, , Int. J. Appl. Ceram. Technol, 18(3), pp.1052~1062 (2021)
- G. Wan, , Ceram. Int, 48(8), pp.11085~11093 (2022)
- R. Alamsyah, , Sci. Res. J, 4, pp.41~45 (2019)
- B. Zorić, , ISA Trans, 125(6), pp.400~414 (2022)
- X. Yu, , Appl. Sci, 13(21), pp.12057~ (2023)
- O. Stephen, , Electronics, 11(1), pp.55~ (2021)
- S. Ye, , J. Phys. : Conf. Ser, 1650(3), pp.032045~ (2020)
- K. B. Kim, , Indones. J. Electr. Eng. Comput. Sci, 19(3), pp.1505~1511 (2020)
- N. T. Huynh, , Sustainability, 15(6), pp.5455~ (2023)
- Z. Zhou, , Sensors, 19(22), pp.5000~ (2019)
- K. Wang, , Appl. Sci, 12(3), pp.1249~ (2022)
- M. F. Ohemu, , ATBU J. Sci. Technol. Educ, 10(2), pp.170~180 (2022)
- A. Ravendran, , J. Comput. Appl. Res. Mech. Eng, 10(2), pp.391~404 (2021)
- J. Wang, , Appl. Sci, 11(1), pp.283~ (2020)
- H. S. Nogay, , Neural Comput. Appl, 34(2), pp.1423~1432 (2022)
- J. Wang, "Investigation on distributed rescheduling with cutting tool maintenance based on nsga-iii in largescale panel furniture intelligent manufacturing", Journal of Manufacturing Processes, 112, pp.214~224 (2024)
- F. Sušac, , Bull. Pol. Acad. Sci. Tech. Sci, 69(3), pp.137121~ (2021)
- Oglakci, B, "The Effect of Different Polishing Systems on the Surface Roughness of Nanocomposites:Contact Profilometry and SEM Analyses", Operative Dentistry, 46(2), pp.173~187 (2021)
- S. Boovaneswari, , Semicond. Optoelectron, 42(1), pp.1082~1095 (2023)
- W. Qian, , J. Phys. : Conf. Ser, 2044(1), pp.012105~ (2021)
- X. Le, , Neurocomputing, 408(9), pp.112~120 (2020)
- G. S. Junior, , Appl. Sci, 11(13), pp.6017~ (2021)
- H. R. Ravikumar, , Int. J. Innov. Sci. Eng. Technol, 7(2), pp.252~263 (2020)
- K. Avazov, , Sensors, 23(16), pp.7078~ (2023)
- S. Gundu, , Sensors, 23(5), pp.2569~ (2023)
- P. Banerjee, , Expert Syst. Appl, 113(12), pp.100~115 (2018)
- F. Bianconi, , J. Imaging, 7(11), pp.245~ (2021)
- H. Kim, "Unsupervised segmentation of microstructural images of steel using data mining methods", Computational Materials Science, 201(5), pp.110855~ (2022)
- G. Lambard, "Generation of highly realistic microstructural images of alloys from limited data with a style-based generative adversarial network", Scientific Reports, 13(1), pp.566~ (2023)
- L. Abualigah, , Gandomi, Comput. Methods Appl. Mech. Eng, 376(4), pp.113609~ (2021)
- D. Bhatt, , Electronics, 10(20), pp.2470~ (2021)
- E. Cumbajin, , J. Imaging, 9(10), pp.193~ (2023)