Application of Hidden Markov Tree Model to On-line Detection of Surface Defects for Steel Strips
Open accessAbstract
摘要： 通过图像分割算法寻找由缺陷组成的可疑区域是热轧带钢表面缺陷在线检测与识别的关键。将热轧带钢表面图像分为“背景”和“缺陷”两大类，采用隐马尔可夫树(Hidden Markov tree，HMT)模型分别建模并实现多尺度缺陷分割。将不同类别的缺陷用同一个“缺陷模型”来表示，可以降低算法复杂度。HMT模型对带钢表面常见缺陷的分割正确率达到94.4%，分割错误率为18.8%。针对HMT模型得到的细尺度分割结果中分割错误率较高问题，引入基于环境的多尺度融合方法(Context-adaptive hidden Markov tree, CAHMT)，将不同尺度的分割结果融合，大幅降低细尺度分割的分割错误率，达到3.7%。
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
Xu et al. decreased the detection false rate from 18.8% to 3.7% using the context-adaptive hidden Markov tree model (CAHMT).
“Further, Xu et al. [89] dramatically decreased the detection false rate from 18.8% to 3.7% by using the proposed context-adaptive hidden Markov tree model (CAHMT) based on an assertion that the correlation of wavelet coefficients of flat steel surface images at different scales satisfies Markov property.”
From Automated Visual Defect Detection for Flat Steel Surface: A Survey (2020) · cites this paper as [89]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Wavelet-based statistical signal processing using hidden Markov models
Crouse, M. S., Nowak, R. D., & Baraniuk, R. G. (1998) · IEEE Transactions on Signal Processing · doi:10.1109/78.668544 · Cited by 1,631 · see citing works
IEEE Transactions on Image Processing
del Conocimiento, D. D. G. (2021) · Universidad Peruana de Ciencias Aplicadas (UPC) · Cited by 1,539 · see citing works
IEEE Transactions on Signal Processing
(2023) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.78 · Cited by 1,459 · see citing works
Bayesian tree-structured image modeling using wavelet-domain hidden Markov models
Romberg, J., Choi, H., & Baraniuk, R. G. (2001) · IEEE Transactions on Image Processing · doi:10.1109/83.931100 · Cited by 496 · see citing works
Multiscale image segmentation using wavelet-domain hidden Markov models
Choi, H.-H., & Baraniuk, R. G. (2001) · IEEE Transactions on Image Processing · doi:10.1109/83.941855 · Cited by 358 · see citing works
Bayesian approach to best basis selection
Pesquet, J., Krim, H., Leporini, D., et al. (2002) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.1996.548005 · Cited by 55 · see citing works
Technology of On-line Surface Inspection for Hot-rolled Steel Strips and Its Industrial Application
Xu, K. (2009) · Journal of Mechanical Engineering · doi:10.3901/jme.2009.04.111 · Cited by 22 · see citing works
Self-citationKalavathy, S., & Suresh, R. M. (2010) · doi:10.1109/icsip.2010.5697519 · Cited by 1 · see citing works
Flagged first, then by citations
Research works printed but not linked: 3
- [3]3. XU Ke, ZHOU Maogui, XU Jinwu, et al. On-line surface inspection system for hot-rolled strips based on liner laser[J]. Journal of University of Science and Technology Beijing, 2008, 30(1) 77-79.
- [11]11. JIAO Licheng, SUN Qiang. Advances and perspective on image perception and recognition in multiscale transform domains[J]. Chinese Journal of Computers, 2006, 29(2) 177-193.
- [16]16. SONG Jinping, HOU Yuhua, YANG Xiaoyi, et al. Context-adapted document segmentation based on multi-state hidden markov tree model in the wavelet domain[J]. Chinese Journal of Electronics, 2007, 35(1) 118-122. 67(89:;)<=<1972 >?@<ABC<DEAB@F GHIJABK%LMNO& PQ&RSTUVWXYZH E-mail[xuke@ustb.edu.cn
Cited by
Sorted by citations
Automated Visual Defect Detection for Flat Steel Surface: A Survey
Luo, Q., Fang, X., Liu, L., Yang, C., & Sun, Y. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2019.2963555 · Cited by 559 · see citing works
Steel Surface Defect Recognition: A Survey
Wen, X., Shan, J., He, Y., & Song, K. (2022) · Coatings · doi:10.3390/coatings13010017 · Cited by 191 · see citing works
- Authors
- XU, K.
- Affiliations
- University of Science and Technology Beijing (CN)
- Corresponding author
- XU, Ke
- ORCID
- XU, Ke
- Venue
- Journal of Mechanical Engineering
- Published
- 2013
- Volume
- 49
- Issue
- 22
- Pages
- 34
- ISSN
- 0577-6686 (ISSN-L)
- OpenAlex
- W2313331974
- Semantic Scholar
- 04609b7a7805fe5c2fa96ee1bc906368fcf0a556
- Cited by
- 16
- References
- 8
- Citations by year
- 2024: 2 · 2023: 2 · 2022: 6 · 2021: 2 · 2020: 2 · 2019: 1 · 2018: 1
- FWCI
- 0.00
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Journal of Mechanical Engineering (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
- hidden Markov tree, online defect detection, image segmentation, multi-scale segmentation, multi-scale fusion, hot-rolled steel, defect classification
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
