Generalized Completed Local Binary Patterns for Time-Efficient Steel Surface Defect Classification
Open accessThe DOI matches its Crossref record; 35 of the 38 references it cites were found in a registry or an index.
Abstract
Efficient defect classification is one of the most important preconditions to achieve online quality inspection for hot-rolled strip steels. It is extremely challenging owing to various defect appearances, large intraclass variation, ambiguous interclass distance, and unstable gray values. In this paper, a generalized completed local binary patterns (GCLBP) framework is proposed. Two variants of improved completed local binary patterns (ICLBP) and improved completed noise-invariant local-structure patterns (ICNLP) under the GCLBP framework are developed for steel surface defect classification. Different from conventional local binary patterns variants, descriptive information hidden in nonuniform patterns is innovatively excavated for the better defect representation. This paper focuses on the following aspects. First, a lightweight searching algorithm is established for exploiting the dominant nonuniform patterns (DNUPs). Second, a hybrid pattern code mapping mechanism is proposed to encode all the uniform patterns and DNUPs. Third, feature extraction is carried out under the GCLBP framework. Finally, histogram matching is efficiently accomplished by simple nearest-neighbor classifier. The classification accuracy and time efficiency are verified on a widely recognized texture database (Outex) and a real-world steel surface defect database [Northeastern University (NEU)]. The experimental results promise that the proposed method can be widely applied in online automatic optical inspection instruments for hot-rolled strip steel.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Multiresolution gray-scale and rotation invariant texture classification with local binary patterns
Ojala, T., Pietikainen, M., & Maenpaa, T. (2002) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2002.1017623 · Cited by 15,398 · cited 2×
“ilar to the experiment setups in [15], [24], [26], we select two commonly used test suites of Outex_TC_00010 (TC10)”
BackgroundMethodA comparative study of texture measures with classification based on featured distributions
Ojala, T., Pietikäinen, M., & Harwood, D. (1996) · Pattern Recognition · doi:10.1016/0031-3203(95)00067-4 · Cited by 6,882 · cited 2×
“[14], [15] claimed that most of the nonuniform patterns made little contribution to texture representation statistically, since uniform patterns always dominate the prior knowledge of texture images.”
BackgroundFace Description with Local Binary Patterns: Application to Face Recognition
Ahonen, T., Hadid, A., & Pietikainen, M. (2006) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2006.244 · Cited by 5,584
Dynamic Texture Recognition Using Local Binary Patterns with an Application to Facial Expressions
Zhao, G., & Pietikainen, M. (2007) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2007.1110 · Cited by 2,846
Enhanced Local Texture Feature Sets for Face Recognition Under Difficult Lighting Conditions
Tan, X., & Triggs, B. (2010) · IEEE Transactions on Image Processing · doi:10.1109/tip.2010.2042645 · Cited by 2,842
A Completed Modeling of Local Binary Pattern Operator for Texture Classification
Guo, Z., Zhang, L., & Zhang, D. (2010) · IEEE Transactions on Image Processing · doi:10.1109/tip.2010.2044957 · Cited by 2,115 · cited 3×
“ilar to the experiment setups in [15], [24], [26], we select two commonly used test suites of Outex_TC_00010 (TC10)”
BackgroundMethodSong, K., & Yan, Y. (2013) · Applied Surface Science · doi:10.1016/j.apsusc.2013.09.002 · Cited by 1,026 · cited 8×
“The noise robust AECLBP and CNLP promote the classification score of CLBP from 97.21% to 98.11% and 98.33%, respectively.”
BackgroundMethodInfluentialDominant Local Binary Patterns for Texture Classification
Liao, S., Law, M. W. K., & Chung, A. C. S. (2009) · IEEE Transactions on Image Processing · doi:10.1109/tip.2009.2015682 · Cited by 785 · cited 11×
“First, GCLBP-series descriptors completely keep pattern information, i.e., only frequencies of specified patterns are extracted in ICLBP and ICNLP, while DLBP neglect pattern information.”
BackgroundMethodInfluentialOutex - new framework for empirical evaluation of texture analysis algorithms
Ojala, T., Maenpaa, T., Pietikainen, M., Viertola, J., Kyllonen, J., & Huovinen, S. (2003) · Object recognition supported by user interaction for service robots · doi:10.1109/icpr.2002.1044854 · Cited by 695 · cited 9×
“database (Outex [28]) and an actual steel surface defect database (NEU [29]).”
BackgroundMethodInfluentialMedian Robust Extended Local Binary Pattern for Texture Classification
Liu, L., Lao, S., Fieguth, P. W., Guo, Y., Wang, X., & Pietikäinen, M. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2522378 · Cited by 431 · cited 1×
“This descriptor and its various variants, such as completed LBP (CLBP) [24], completed noise-invariant local-structure pattern (CNLP) [25], and dominant LBP (DLBP) [26], have been successfully applied to face recognition [17]–[19], texture classification [20], [21], and visual tracking [22].”
BackgroundAutomatic Defect Detection on Hot-Rolled Flat Steel Products
Ghorai, S., Mukherjee, A., Gangadaran, M., & Dutta, P. K. (2013) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2012.2218677 · Cited by 317 · cited 2×
“The gray value is sensitive to cooling water [4], uneven illumination [5], multiple material types [8], and mechanical vibration [3], [9].”
BackgroundPairwise Rotation Invariant Co-Occurrence Local Binary Pattern
Qi, X., Xiao, R., Li, C.-G., Qiao, Y., Guo, J., & Tang, X. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2316826 · Cited by 296
Image Quality Assessment Based on Multiscale Geometric Analysis
Gao, X., Lu, W., Tao, D., & Li, X. (2009) · IEEE Transactions on Image Processing · doi:10.1109/tip.2009.2018014 · Cited by 252 · cited 1×
“Various algorithms such as multi-scale geometric analysis [10], Bayes theorem [11], support vector machine [12], the aforementioned VVRKFA [6], and the latest CNN [13] can be used for feature extraction and matching.”
MethodNoise-Resistant Local Binary Pattern With an Embedded Error-Correction Mechanism
Ren, J., Jiang, X., & Yuan, J. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2013.2268976 · Cited by 218
Discriminative features for texture description
Guo, Y., Zhao, G., & Pietikäinen, M. (2012) · Pattern Recognition · doi:10.1016/j.patcog.2012.04.003 · Cited by 208
Dominant Rotated Local Binary Patterns (DRLBP) for texture classification
Mehta, R., & Egiazarian, K. (2016) · Pattern Recognition Letters · doi:10.1016/j.patrec.2015.11.019 · Cited by 188 · cited 1×
“This descriptor and its various variants, such as completed LBP (CLBP) [24], completed noise-invariant local-structure pattern (CNLP) [25], and dominant LBP (DLBP) [26], have been successfully applied to face recognition [17]–[19], texture classification [20], [21], and visual tracking [22].”
BackgroundKirkland, E. J. (2010) · Advanced Computing in Electron Microscopy · doi:10.1007/978-1-4419-6533-2_12 · Cited by 182
An End‐to‐End Steel Strip Surface Defects Recognition System Based on Convolutional Neural Networks
Yi, L., Li, G., & Jiang, M. (2017) · steel research international · doi:10.1002/srin.201600068 · Cited by 173 · cited 1×
“Various algorithms such as multi-scale geometric analysis [10], Bayes theorem [11], support vector machine [12], the aforementioned VVRKFA [6], and the latest CNN [13] can be used for feature extraction and matching.”
MethodSteel Surface Defect Detection Using a New Haar–Weibull-Variance Model in Unsupervised Manner
Liu, K., Wang, H., Chen, H., Qu, E., Tian, Y., & Sun, H. (2017) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2017.2712838 · Cited by 161 · cited 1×
“[7] constructed an unsupervised Haar-Weibull-variance model, and a”
MethodCompleted robust local binary pattern for texture classification
Zhao, Y., Jia, W., Hu, R.-X., & Min, H. (2013) · Neurocomputing · doi:10.1016/j.neucom.2012.10.017 · Cited by 159
A cost-effective and automatic surface defect inspection system for hot-rolled flat steel
Luo, Q., & He, Y. (2016) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2015.09.008 · Cited by 129 · cited 3×
“As for our AOI instrument developed in [4], the average permitted classification time per image sample (256 × 256 pixel) can be estimated as tce = Tbusy × λ1 + Tidle ndps × (L/himage × λ2) = 200 s × 0.”
BackgroundMethodSelf-citationCombining LBP Difference and Feature Correlation for Texture Description
Hong, X., Zhao, G., Pietikainen, M., & Chen, X. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2316640 · Cited by 120
Detection of surface defects on raw steel blocks using Bayesian network classifiers
Pernkopf, F. (2004) · Pattern Analysis and Applications · doi:10.1007/s10044-004-0232-3 · Cited by 113 · cited 1×
“Various algorithms such as multi-scale geometric analysis [10], Bayes theorem [11], support vector machine [12], the aforementioned VVRKFA [6], and the latest CNN [13] can be used for feature extraction and matching.”
Method3D face recognition using local binary patterns
Tang, H., Yin, B., Sun, Y., & Hu, Y. (2012) · Signal Processing · doi:10.1016/j.sigpro.2012.04.002 · Cited by 108 · cited 1×
“This descriptor and its various variants, such as completed LBP (CLBP) [24], completed noise-invariant local-structure pattern (CNLP) [25], and dominant LBP (DLBP) [26], have been successfully applied to face recognition [17]–[19], texture classification [20], [21], and visual tracking [22].”
BackgroundSelf-citationEvaluation of noise robustness for local binary pattern descriptors in texture classification
Kylberg, G., & Sintorn, I. (2013) · EURASIP Journal on Image and Video Processing · doi:10.1186/1687-5281-2013-17 · Cited by 94 · cited 1×
“This paper investigated that the local binary patterns (LBP) descriptor is lightweight and efficient for texture representation [14]–[16].”
BackgroundRobust Visual Detection–Learning–Tracking Framework for Autonomous Aerial Refueling of UAVs
Yin, Y., Wang, X., Xu, D., Liu, F., Wang, Y., & Wu, W. (2016) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2015.2509318 · Cited by 77 · cited 1×
“This descriptor and its various variants, such as completed LBP (CLBP) [24], completed noise-invariant local-structure pattern (CNLP) [25], and dominant LBP (DLBP) [26], have been successfully applied to face recognition [17]–[19], texture classification [20], [21], and visual tracking [22].”
BackgroundAccurate and Efficient Inspection of Speckle and Scratch Defects on Surfaces of Planar Products
Kong, H., Yang, J. J., & Chen, Z. (2017) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2017.2668438 · Cited by 69 · cited 1×
“The gray value is sensitive to cooling water [4], uneven illumination [5], multiple material types [8], and mechanical vibration [3], [9].”
BackgroundClassification of defects in steel strip surface based on multiclass support vector machine
Hu, H., Li, Y., Liu, M., & Liang, W. (2014) · Multimedia Tools and Applications · doi:10.1007/s11042-012-1248-0 · Cited by 68 · cited 1×
“Various algorithms such as multi-scale geometric analysis [10], Bayes theorem [11], support vector machine [12], the aforementioned VVRKFA [6], and the latest CNN [13] can be used for feature extraction and matching.”
MethodAdaptive surface inspection via interactive evolution
Caleb-Solly, P., & Smith, J. E. (2007) · Image and Vision Computing · doi:10.1016/j.imavis.2006.04.023 · Cited by 48
A fast method of steel surface defect detection using decision trees applied to LBP based features
Aghdam, S. R., Amid, E., & Imani, M. F. (2012) · 2012 7th IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea.2012.6360951 · Cited by 46 · cited 1×
“Some literatures on surface defect inspection based on LBP are reported [8], [23].”
BackgroundMulti-scale Joint Encoding of Local Binary Patterns for Texture and Material Classification
Qi, X., Qiao, Y., Li, C., & Guo, J. H. (2013) · British Machine Vision Conference (BMVC) · doi:10.5244/c.27.40 · Cited by 35
Ghorai, S., Mukherjee, A., & Dutta, P. K. (2010) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2010.2046646 · Cited by 28 · cited 3×
“[6] proposed a typical supervised learning algorithm-vector-valued regular-”
BackgroundMethodSUGIMOTO, T., & Kawaguchi, T. (1998) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/19.744183 · Cited by 26 · cited 1×
“In general, defect detection and defect classification are two main functions of AOI instruments [1]–[8].”
BackgroundVibrations in Steel Strips: Effects on Flatness Measurement and Filtering
Usamentiaga, R., Garcia, D. F., Molleda, J., Bulnes, F. G., & Bonet Brana, G. (2014) · IEEE Transactions on Industry Applications · doi:10.1109/tia.2014.2308359 · Cited by 21
Noise-invariant structure pattern for image texture classification and retrieval
Shrivastava, N., & Tyagi, V. (2015) · Multimedia Tools and Applications · doi:10.1007/s11042-015-2811-2 · Cited by 13 · cited 3×
“Any other CLBP-like variant such as CRLBP [36] or CNLP [25] can be strengthened to improved complete robust local binary patterns or ICNLP, respectively.”
BackgroundMethod
Research works printed but not linked: 1
- song, 2014, Automatic recognition of surface defects on hot-rolled steel strip using scattering convolution network, J Comput Inf Syst, 10, 3049
Cited by
Dong, H., Song, K., He, Y., Xu, J., Yan, Y., & Meng, Q. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2958826 · Cited by 559
“Other approaches based on hand crafted feature are used for defect detection in industrial applications (such as solar modules [3], metal [4], and steel [5]) and have achieved good result in recent years.”
BackgroundSelf-citationAutomated 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
“Using reverse thinking, Luo et al. [3] proposed a generalized completed LBPs (GCLBP) by first exploring the nonuniform patterns to supplement the descriptive information in uniform patterns.”
Self-citationEDRNet: Encoder–Decoder Residual Network for Salient Object Detection of Strip Steel Surface Defects
Song, G., Song, K., & Yan, Y. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3002277 · Cited by 309
“As a fast image preprocessing operation, it has been widely used in various computer vision tasks including image segmentation [3], defect classification [4]–[6], defect inspection [7]–[12], and object tracking [13].”
MethodRecent advances in surface defect inspection of industrial products using deep learning techniques
Zheng, X., Zheng, S., Kong, Y., & Chen, J. (2021) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-021-06592-8 · Cited by 287
“Luo et al. [37] proposed a generalized completed local binary pattern framework with two variants for steel surface defect classification, in 2018.”
BackgroundReview of surface defect detection of steel products based on machine vision
Tang, B., Chen, L., Sun, W., & Lin, Z. (2023) · IET Image Processing · doi:10.1049/ipr2.12647 · Cited by 271
Metadata
- Authors
- Luo, Q., Sun, Y., Li, P., Simpson, O., Tian, L., & He, Y.
- Affiliations
- Central South University (CN)
- University of Hertfordshire (GB)
- Hefei University of Technology (CN)
- Wuhan University (CN)
- Venue
- IEEE Transactions on Instrumentation and Measurement
- Published
- 2019-03
- Volume
- 68
- Issue
- 3
- Pages
- 667-679
- ISSN
- 0018-9456 (ISSN-L)
- 1557-9662
- OpenAlex
- W2884563051
- Cited by
- 178
- References
- 38
- Citations by year
- 2026: 12 · 2025: 30 · 2024: 32 · 2023: 27 · 2022: 22 · 2021: 25 · 2020: 20 · 2019: 10
- FWCI
- 11.36
- Type
- journal article
- Language
- en
- Open access
- green
- hdl.handle.net
- Licence
- Locations
- IEEE Transactions on Instrumentation and Measurement (publishedVersion)
- University of Hertfordshire Research Archive (University of Hertfordshire) (acceptedVersion, other-oa)
- University of Hertfordshire Research Archive (University of Hertfordshire) (submittedVersion)
- Funders
- National Natural Science Foundation of China (51704089, 51577046, 51637004)
- Natural Science Foundation of Anhui Province (1808085QF190)
- China Postdoctoral Science Foundation (2017M621996)
- Fundamental Research Funds for the Central Universities of China (JZ2018YYPY0296)
- National Key Research and Development Plan “Important Scientific Instruments and Equipment Development” (2016YFF0102200)
- Topics
- Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Physical Sciences › Engineering › Mechanical Engineering › Non-Destructive Testing Techniques
- Keywords
- completed local binary pattern, hot-rolled strip steel, texture features, histogram matching, nearest neighbor classification, online quality inspection, automated optical inspection, feature extraction
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.