The Strip Steel Surface Defects Classification Method Based on Weak Classifier Adaptive Enhancement
Abstract
The contradiction between algorithm complexity and classification accuracy exists in current strip steel surface defects detection system classification method. In order to solve the above problem, weak classifier adaptive enhancement classification method is presented in this paper. In this method presented in this paper, weak classifiers will focus on the samples that are difficult to distinguish, by adaptively changing the distribution of the weights of training samples, so that it can reduce the error of classification, and greatly improve the effectiveness of feature classification. The experimental results show that this method has higher accuracy of classification than other methods in steel surface defect classification, and solved the contradiction between algorithm complexity and classification accuracy better, so the method has certain value for engineering application.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
A cascaded weak classifier composed of several weak classifiers based on extended Haar rectangle features was compared with KNN, NN-BP and SVM for cold-rolled strips in [82].
“Yunhui et al. [82]: To study the problem of achieving classification accuracy at the cost of complexity of algorithm, a cascaded weak classifier composed of several weak classifiers (based on extended Haar rectangle features) has been compared with KNN, NN-BP and SVM for cold-rolled strips.”
From Review of vision-based steel surface inspection systems (2014) · cites this paper as [82]
The weak classifier approach achieved a best overall result of 94% for six types of defects in cold strips.
“Superiority of weak classifier (best overall result 94%) is documented for six types of defects in cold strips.”
From Review of vision-based steel surface inspection systems (2014) · cites this paper as [82]
AVI systems relying on multi-classifiers can achieve better classification performance and robustness than those based on individual classifiers.
“AVI systems relying on multi-classifiers can achieve better classification performance and robustness than those based on individual classifiers.”
From Automated Visual Defect Classification for Flat Steel Surface: A Survey (2020) · cites this paper as [123]
Cites
Rapid object detection using a boosted cascade of simple features
Viola, P., & Jones, M. (2005) · Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 · doi:10.1109/cvpr.2001.990517 · Cited by 18,300 · see citing works
Robust Real-Time Face Detection
Viola, P., & Jones, M. J. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000013087.49260.fb · Cited by 14,097 · see citing works
An extended set of Haar-like features for rapid object detection
Lienhart, R., & Maydt, J. (2003) · Proceedings. International Conference on Image Processing · doi:10.1109/icip.2002.1038171 · Cited by 2,977 · cited 1× · see citing works
“It has important theoretical and economic value to research on the recognition and classification of surface defects in the steel strip [1]-[3].”
BackgroundReal-Time Flatness Inspection System For Steel Strip Production Lines
Garcia, D. F., García, M., Obeso, F., & Fernandez, V. (1999) · Real-Time Imaging · doi:10.1006/rtim.1998.0146 · Cited by 13 · see citing works
Real-time system for flatness inspection of steel strips
López, C. M., Garcia, D. F., Usamentiaga, R., González, D., & Gonzalez, J. A. (2005) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.585902 · Cited by 12 · see citing works
Winner Trace Marking in Self-Organizing Neural Network for Classification
Wang, Y., Yan, Y., & Wu, Y. (2008) · International Symposium on Computer Science and Computational Technology · doi:10.1109/iscsct.2008.133 · Cited by 4 · see citing works
Inspection method for directional texture defects on steel strip surface
Cong, J.-H., & Yan, Y. (2008) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.814524 · Cited by 1 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Review of vision-based steel surface inspection systems
Neogi, N., Mohanta, D. K., & Dutta, P. K. (2014) · EURASIP Journal on Image and Video Processing · doi:10.1186/1687-5281-2014-50 · Cited by 322 · see citing works
“[82] - cold strip Weak classifier Serrated edge, scratch, shell, inclusion, weld, wrinkles.”
MethodAutomated Visual Defect Classification for Flat Steel Surface: A Survey
Luo, Q., Fang, X., Su, J., Zhou, J., Zhou, B., Yang, C., Liu, L., Gui, W., & Tian, L. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3030167 · Cited by 148 · see citing works
Chu, M., Gong, R., Gao, S., & Zhao, J. (2017) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2017.10.020 · Cited by 97 · see citing works
Defect detection of steel surface using entropy segmentation
Nand, G. K., Noopur, & Neogi, N. (2014) · 2014 Annual IEEE India Conference (INDICON) · doi:10.1109/indicon.2014.7030439 · Cited by 44 · see citing works
Gong, R., Wu, C., & Chu, M. (2018) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2017.11.018 · Cited by 44 · see citing works
ACD‐YOLO: Improved YOLOv5‐based method for steel surface defects detection
Fan, J., Wang, M., Li, B., Liu, M., & Shen, D. (2023) · IET Image Processing · doi:10.1049/ipr2.12983 · Cited by 31 · see citing works
A multi-class classifier based on support vector hyper-spheres for steel plate surface defects
Gong, R., Chu, M., Yang, Y., & Feng, Y. (2019) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2019.03.010 · Cited by 31 · see citing works
Chu, M., Zhao, J., Gong, R., & Liu, L. (2017) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2017.7979072 · Cited by 11 · see citing works
Analyzing Embedded AIoT Devices for Deep Learning Purposes
Budjač, R., Bartoň, M., Schreiber, P. P., & Skovajsa, M. (2022) · Lecture notes in networks and systems · doi:10.1007/978-3-031-09076-9_39 · Cited by 4 · see citing works
Comparison Of Iron And Steel Production Defects Using Classification Algorithms
Akinci, I. B., Alobaidi, D., & Ersöz, F. (2021) · International Congress on Human-Computer Interaction, Optimization and Robotic Applications (ICHORA) · doi:10.1109/hora52670.2021.9461299 · Cited by 2 · see citing works
- Authors
- Yunhui, Y., Kechen, S., Zhitao, X., & Xuehui, F.
- Affiliations
- Northeastern University (CN)
- Venue
- 2011 Third International Conference on Measuring Technology and Mechatronics Automation
- Publisher
- IEEE
- Published
- 2011-01
- Pages
- 958-961
- OpenAlex
- W2117780789
- Cited by
- 11
- References
- 8
- Citations by year
- 2023: 1 · 2022: 1 · 2021: 1 · 2020: 1 · 2019: 1 · 2017: 3 · 2016: 1 · 2014: 2
- FWCI
- 1.85
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on Measuring Technology and Mechatronics Automation (ICMTMA) (publishedVersion)
- Topics
- Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
- Physical Sciences › Engineering › Mechanical Engineering › Non-Destructive Testing Techniques
- Physical Sciences › Engineering › Civil and Structural Engineering › Infrastructure Maintenance and Monitoring
- Keywords
- defect classification, weak classifiers, adaptive boosting, algorithmic complexity, classification accuracy
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
