Automatic Defect Detection on Hot-Rolled Flat Steel Products
The DOI matches its Crossref record; 25 of the 25 references it cites were found in a registry or an index.
Abstract
Automatic defect detection on hot-rolled steel surface is challenging owing to its localization on a large surface, variation in appearance, and their rare occurrences. It is difficult to detect these defects either by physics-based models or by small-sample statistics using a single threshold. As a result, this problem is focused to derive a set of good-quality defect descriptors from the surface images. These descriptors should discriminate the various surface defects when fed to suitable machine learning algorithms. This research work has evaluated the performance of a number of different wavelet feature sets, namely, Haar, Daubechies 2 (DB2), Daubechies 4 (DB4), biorthogonal spline, and multiwavelet in different decomposition levels derived from 32 × 32 contiguous (nonoverlapping) pixel blocks of steel surface images. We have developed an automated visual inspection system for an integrated steel plant to capture surface images in real time. It localizes defects employing kernel classifiers, such as support vector machine and recently proposed vector-valued regularized kernel function approximation. Test results on 1000 defect-free and 432 defective images comprising of 24 types of defect classes reveal that three-level Haar feature set is more promising to address this problem than the other wavelet feature sets as well as texture-based segmentation or thresholding technique of defect detection.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
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?
In the citing paper
“The central outcome of this paper, based on test results on 24 types of defect classes, was that the wavelet feature sets were better suited for steel surface defect detection application compared to texture-based segmentation or thresholding techniques.”
From Review of vision-based steel surface inspection systems (2014) · cites this paper as [70]
In the citing paper
“Further, three-level Haar feature set is more promising compared to the Daubechies, bior and multiwavelet features.”
From Review of vision-based steel surface inspection systems (2014) · cites this paper as [70]
In the citing paper
“In an elaborate study [70], five different types of wavelets, namely, Haar, Daubechies2 (DB2), Daubechies 4 (DB4), biorthogonal spline (bior) and multiwavelet, were used to extract features by decomposing the small blocks (32 × 32) of surface images into different resolution levels.”
From Review of vision-based steel surface inspection systems (2014) · cites this paper as [70]
In the citing paper
“With VVRKFA classification accuracy of 94% was achieved.”
From Review of vision-based steel surface inspection systems (2014) · cites this paper as [70]
In the citing paper
“Lee et al. [72] (cold strip application) and [70] (hot strip application) used wavelet-based methods to classify 8 types and 24 types of defects, respectively.”
From Review of vision-based steel surface inspection systems (2014) · cites this paper as [70]
7 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
The Nature of Statistical Learning Theory
Vapnik, V. N. (1995) · doi:10.1007/978-1-4757-2440-0 · Cited by 39,138
A Wavelet Tour of Signal Processing
(1999) · Elsevier eBooks · doi:10.1016/b978-0-12-466606-1.x5000-4 · Cited by 16,227 · cited 2×
“An iterative computational approach to the DWT [21], [22] is shown in Fig.”
MethodAn Introduction to Support Vector Machines and Other Kernel-based Learning Methods
Cristianini, N., & Shawe-Taylor, J. (2000) · doi:10.1017/cbo9780511801389 · Cited by 13,855
Libsvm : A library for support vector machines
Ferrari, V. (2008) · Medical Entomology and Zoology · Cited by 10,122
An Introduction to Support Vector Machines
Cristianini, N., & Shawe-Taylor, J. S. (2000) · ePrints Soton (University of Southampton) · Cited by 4,115
Digital Image Processing: PIKS Scientific Inside
Pratt, W. K. (2007) · Wiley eBooks · doi:10.1002/0470097434 · Cited by 2,616
Linear algebra and its applications
(1981) · Linear Algebra and its Applications · doi:10.1016/0024-3795(81)90106-3 · Cited by 872
Computer-Vision-Based Fabric Defect Detection: A Survey
Kumar, A. (2008) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.1930.896476 · Cited by 725 · cited 1×
“In the literature, there are methods of defect detection inside steel casting [1], on fabric surface [2]–[4], glass plates [5], liquid crystal display images [6], etc.”
MethodKernel Methods for Pattern Analysis
Breneman, J. (2005) · Technometrics · doi:10.1198/tech.2005.s264 · Cited by 426
Nonlinear Dynamic Process Monitoring Using Canonical Variate Analysis and Kernel Density Estimations
Odiowei, P.-E. P., & Cao, Y. (2010) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2009.2032654 · Cited by 361 · cited 1×
“efficiently applied in many industries for automatic detection of faults [12]–[14] as well as for dynamic process monitoring [15].”
Background
Research works printed but not linked: 2
- gonzalez, 2007, Digital Image Processing
- mitchell, 1997, Machine Learning
Cited by
Items 101–200 of 317
Fu, G., Jia, S., Zhu, W., Yang, J., Cao, Y., Yang, M. Y., & Cao, Y. (2022) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2022.109109 · Cited by 35
Cao, Y., Zhu, W., Yang, J., Fu, G., Lin, D., & Cao, Y. (2022) · Optics and Lasers in Engineering · doi:10.1016/j.optlaseng.2022.107294 · Cited by 35
Machine vision based statistical process control in fused deposition modeling
Yi, W., He, K., Xiaomin, Z., & Wenying, D. (2017) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea.2017.8282973 · Cited by 32
“They captured real-time surface images and detect defects by applying machine learning algorithms[19].”
MethodACD‐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 36
Panoramic Crack Detection for Steel Beam Based on Structured Random Forests
Wang, S., Liu, X., Yang, T., & Wu, X. (2018) · IEEE Access · doi:10.1109/access.2018.2812141 · Cited by 36
“[34] adopted vector value normalization of kernel functions to approximate Haar wavelet reconstruction characteristics among three scales.”
MethodOn-Site Reliable Wheel Size Measurement Based on Multisensor Data Fusion
Pan, X., Liu, Z., & Zhang, G. (2019) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2018.2890328 · Cited by 31
“2890328 and other methods [13], [14].”
Vannocci, M., Ritacco, A., Castellano, A., Galli, F., Vannucci, M., Iannino, V., & Colla, V. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20518-8_19 · Cited by 35
Polygon-Invariant Generalized Hough Transform for High-Speed Vision-Based Positioning
Yang, H. S., Zheng, S., Lu, J. L., & Yin, Z. (2016) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2016.2569558 · Cited by 30
“A modified GHT using displacement vectors instead of the gradient direction to eliminate the rotation degree of HCS freedom is described in [48]; this method loses the orientation angle information of an object with respect to the same object in the template image.”
MethodA Fast Magnetic Flux Leakage Small Defect Detection Network
Han, F., & Lang, X. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2023.3280950 · Cited by 33
Research on steel surface defect classification method based on deep learning
Gao, Y., Lv, G., Xiao, D., Han, X., Sun, T., & Li, Z. (2024) · Scientific Reports · doi:10.1038/s41598-024-58643-1 · Cited by 41
A Novel Technique of Black Tea Quality Prediction Using Electronic Tongue Signals
Saha, P., Ghorai, S., Tudu, B., Bandyopadhyay, R., & Bhattacharyya, N. (2014) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2014.2310615 · Cited by 28
“The performance of the proposed feature set has been assessed by two different kernel classifiers namely, multiclass support vector machine (SVM) [26]–[29], and recently developed vector valued regularized kernel function approximation (VVRKFA) [30]–[32], technique of multiclass data classification.”
MethodSelf-citationXu, J., Liu, Y., Xie, H., & Luo, F. (2019) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2019.2929670 · Cited by 28
“In the defect classification of AOIS, many machine learning algorithms have been used for industrial classification decision, such as decision tree [21], [22], neural network [23]–[26], genetic algorithm [27], [28], K-nearest neighbor (KNN) [3], [29], support vector machine (SVM) [29], [30], Bayes [31], AdaBoost [15],…”
MethodWu, B., Zhou, J., Ji, X., Yin, Y., & Shen, X. (2019) · Procedia Manufacturing · doi:10.1016/j.promfg.2019.12.065 · Cited by 32
Steel Strip Surface Defect Identification using Multiresolution Binarized Image Features
Mentouri, Z., Moussaoui, A., Boudjehem, D., & Doghmane, H. (2020) · Journal of Failure Analysis and Prevention · doi:10.1007/s11668-020-01012-7 · Cited by 31
Navarro, P., Fernández-Isla, C., Alcover, P. M., & Muro, J. S. (2016) · Sensors · doi:10.3390/s16081178 · Cited by 27
“Wavelet transform has resulted in two groups of techniques for detecting defects: (1) direct thresholding methods [25,44–47], whose operation is based on the background attenuation provided by the WT in the successive decomposition levels (such attenuation allows enhancing defects, which can be segmented by utilizing…”
MethodA Single-Stage Enhancement-Identification Framework for Pipeline MFL Inspection
Feng, J. Y., Zhang, X., Lu, S., & Yang, F. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3176285 · Cited by 29
Steel Surface Defect Classification Based on Discriminant Manifold Regularized Local Descriptor
Zhao, J., Peng, Y., & Yan, Y. (2018) · IEEE Access · doi:10.1109/access.2018.2881962 · Cited by 26
A Survey on Surface Defect Inspection Based on Generative Models in Manufacturing
He, Y., Li, S., Wen, X., & Xu, J. (2024) · Applied Sciences · doi:10.3390/app14156774 · Cited by 35
Surface Defects Detection Using Non-convex Total Variation Regularized RPCA With Kernelization
Wang, J., Xu, G., Li, C., Wang, Z., & Yan, F. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3056738 · Cited by 36
“Ghorai et al. [18] discriminate the various surface defects by feeding a set of defect descriptors to kernel support vector machine.”
BackgroundMethodStrip Steel Defect Classification Using the Improved GAN and EfficientNet
Guan, S., Chang, J., Shi, H., Xiao, X., Li, Z., Wang, X., & Wang, X. (2021) · Applied Artificial Intelligence · doi:10.1080/08839514.2021.1995231 · Cited by 25
Subramanyam, V., Kumar, J., & Singh, S. N. (2022) · Journal of Real-Time Image Processing · doi:10.1007/s11554-022-01198-z · Cited by 24
“The motivation for this paper arises from scenarios of continuous web processes such as steel rolling mills [8, 9], fabric mills where the objective of the DAS is capturing surface defects, as well as the location of defects in real time [10, 11].”
BackgroundReal-time system for automatic cold strip surface defect detection
Kostenetskiy, P., Alkapov, R., Vetoshkin, N., Chulkevich, R., Napolskikh, I., & Poponin, O. (2019) · FME Transactions · doi:10.5937/fmet1904765k · Cited by 23
“The approach was improved to identify more classes, also known as multiclass classification [19],[20].”
MethodYue, X., Ma, G., Liu, F., & Gao, X. (2021) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-210374 · Cited by 21
Unsupervised defect detection with patch-aware mutual reasoning network in image data
Wang, Y., Song, K., Niu, M., Bao, Y., Dong, H., & Yan, Y. (2022) · Automation in Construction · doi:10.1016/j.autcon.2022.104472 · Cited by 22
PAC Interaction Inspection Using Real-Time Contact Point Tracking
Shen, Y., Liu, Z., & Zhang, G. (2018) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2018.2884039 · Cited by 21
FS-RSDD: Few-Shot Rail Surface Defect Detection with Prototype Learning
Min, Y., Wang, Z., Liu, Y., & Wang, Z. (2023) · Sensors · doi:10.3390/s23187894 · Cited by 30
CANet: Context-aware Aggregation Network for Salient Object Detection of Surface Defects
Wan, B., Zhou, X., Zhu, B. B., Xiao, M., Sun, Y., Zheng, B., Zhang, J., & Yan, C. C. (2023) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2023.103820 · Cited by 21
Multiscale Local and Global Feature Fusion for the Detection of Steel Surface Defects
Zhang, L., Fu, Z., Guo, H., Sun, Y., Li, X., & Xu, M. (2023) · Electronics · doi:10.3390/electronics12143090 · Cited by 22
“Ghorai et al. [17] designed a method using the support vector machine (SVM) and a set of wavelet features for the classi fi cation of hot-rolled fl at steel products.”
MethodDuAK: Reinforcement Learning-Based Knowledge Graph Reasoning for Steel Surface Defect Detection
Zhang, Y., Wang, H., Shen, W., & Peng, G. (2023) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2023.3307588 · Cited by 22
MPFANet: a multipath feature aggregation network for steel surface defect detection
Li, Z., Tai, Y., Huang, Z., Peng, T., & Zhang, Z. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad1daf · Cited by 19
Automatic Rail Component Detection Based on AttnConv-Net
Wang, T., Zhang, Z., Yang, F., & Tsui, K. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3132460 · Cited by 23
“The combination of SVM and different feature extractions was also widely applied to address AIRS [15], [16].”
MethodAn End-to-End Steel Surface Classification Approach Based on EDCGAN and MobileNet V2
Jin, G., Liu, Y., Qin, P., Hong, R., Xu, T., & Lu, G. (2023) · Sensors · doi:10.3390/s23041953 · Cited by 23
“use a three-level Haar feature to design an automatic detection algorithm applied to production defects on the surface of steel [8].”
MethodScattering from Rough Surfaces in 100+ GHz Wireless Mobile Networks: From Theory to Experiments
Shen, R., & Ghasempour, Y. (2023) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/3570361.3613306 · Cited by 18
“Accurate imaging of rough surfaces has various applications in clinical diagnosis [10, 11], security check [7, 52], defect detection [24, 54], archaeological analysis [59], and interactive robotics [51, 61].”
BackgroundHosseinzadeh, A., Shahin, M., Maghanaki, M., Mehrzadi, H., & Chen, F. F. (2024) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-024-14741-y · Cited by 19
“Traditional metal surface defect detection methods have primarily relied on manual inspection [5].”
TSEDNet:Task-specific encoder–decoder network for surface defects of strip steel
Guo, Y., Wei, J., & Feng, X. (2024) · Measurement · doi:10.1016/j.measurement.2024.115438 · Cited by 22
Steel Sheet Defect Detection Based on Deep Learning Method
Zeng, W., You, Z., Huang, M., Kong, Z., Yu, Y., & Le, X. (2019) · International Conference on Intelligent Control and Information Processing · doi:10.1109/icicip47338.2019.9012199 · Cited by 19
“For example, some methods find the regions of defects by performing binary classification [4] [5], or only give an imprecise localization of each defect [6] [7].”
MethodProduct failure prediction with missing data using graph neural networks
Kang, S. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-05486-2 · Cited by 17
“Such attempts include monitoring process anomalies [29, 31, 38], intelligent process control [12, 34], estimating intermediate inspections [14, 37], predicting production yield [3, 28], and recognizing individual product failures [9, 20].”
BackgroundDetection of Bubble Defects on Tire Surface Based on Line Laser and Machine Vision
Yang, H., Jiang, Y., Deng, F., Mu, Y., Zhong, Y., & Jiao, D. (2022) · Processes · doi:10.3390/pr10020255 · Cited by 17
“In the aspect of tire bubble detection, the line laser is rarely used, but it is still widely used in three-dimensional scanning [4–11], obtaining distance information [12–17], surface defect detection [18,19], and production detection [20–22].”
MethodFast and Automatic Image Segmentation Using Superpixel-Based Graph Clustering
Jia, X., Lei, T., Liu, P., Xue, D., Meng, H., & Nandi, A. K. (2020) · IEEE Access · doi:10.1109/access.2020.3039742 · Cited by 17
“Image segmentation has been widely used in computer vision [1], remote sensing image analysis [2], biomedical research [3], industrial detection [4], etc. Popular image segmentation algorithms can be organized into two groups: unsupervised and supervised image segmentation.”
MethodResearch on Surface Defect Detection Algorithm of Strip Steel Based on Improved YOLOV3
Zhang, N., & Mi, Z. (2021) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1907/1/012015 · Cited by 17
“However, due to the influence of factors such as production technology and equipment of rolling, surface defects in the process of strip steel production will inevitably produce, such as pitting, inclusion, scratches[1].”
BackgroundA detection model for corner cracks of continuous casting strand based on deep learning
Meng, X., Luo, S., Wang, W., & Zhu, M. (2022) · Ironmaking & Steelmaking Processes Products and Applications · doi:10.1080/03019233.2022.2078262 · Cited by 17
“Recently, in most steel companies in the world, surface defects detection in continuously cast strand still relies on manual inspection [4,5], which is a hard work with a high error rate, and it cannot meet the demand for real-time inspection of strand surface quality.”
BackgroundA Shallow Neural Network for Recognition of Strip Steel Surface Defects Based on Attention Mechanism
Li, D., Ge, S., Zhao, K., & Wang, B. (2022) · ISIJ International · doi:10.2355/isijinternational.isijint-2022-201 · Cited by 17
Wen, X., Song, K., Niu, M., Dong, Z., & Yan, Y. (2016) · Optik · doi:10.1016/j.ijleo.2016.11.050 · Cited by 15
Modeling and recognition of steel-plate surface defects based on a new backward boosting algorithm
Hu, L., Zhou, M., Xiang, F., & Feng, Q. (2017) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-017-1113-4 · Cited by 18
“…steel-plate surface defects usually include k-nearest neighbor (KNN) [9], back propagation neural network (BPNN) [10], support vector machine (SVM) [11], decision tree (DT) [12], naive Bayesian (NB) [13], logistic regression (LR) [14], etc., where the BPNN is the most widely used algorithm for…”
BackgroundMethodInfluentialZheng, X., Liu, W., & Huang, Y. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112179 · Cited by 18
Semi-supervised learning for steel surface inspection using magnetic flux leakage signal
Park, J.-E., & Kim, Y. (2023) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-023-02286-y · Cited by 15
Inception Dual Network for steel strip defect detection
Liu, Z., Wang, X., & Chen, X. (2019) · IEEE International Conference on Networking, Sensing and Control (ICNSC) · doi:10.1109/icnsc.2019.8743190 · Cited by 15
“[3] tried a method based on discrete wavelet transform (DWT) to extract wavelet basis features and detect the defects.”
MethodProcess-Monitoring-for-Quality - A Step Forward in the Zero Defects Vision
Escobar, C. A., Arinez, J. F., & Morales-Menéndez, R. (2020) · SAE technical papers on CD-ROM/SAE technical paper series · doi:10.4271/2020-01-1302 · Cited by 15
Automatic Detection and Quantification of Hot-Rolled Steel Surface Defects Using Deep Learning
Liu, Z., Zeng, Z., Li, J., & Teng, S. (2022) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-022-07567-x · Cited by 16
“A study also employed the SVM to classify hot-rolled flat steel into defect and normal images [15].”
Swin-Transformer -YOLOv5 for lightweight hot-rolled steel strips surface defect detection algorithm
Wang, Q., Dong, H., & Huang, H. (2024) · PLoS ONE · doi:10.1371/journal.pone.0292082 · Cited by 21
Zhang, S., Liu, Z., An, T., Cui, X., Zeng, X., Shi, N., & Su, H. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.123763 · Cited by 14
Improved cross pattern approach for steel surface defect recognition
Mentouri, Z., Doghmane, H., Moussaoui, A., & Bourouba, H. (2020) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-020-06050-x · Cited by 15
“In these methods, numerous wavelet types such as Haar, Daubechies, biorthogonal, and undecimated wavelet transform (UWT) have been applied with a thresholding technique and histogram equalization for the detection of complex defects on steel flat products [4, 5], and have showed a good performance.”
MethodParallel Dilated CNN for Detecting and Classifying Defects in Surface Steel Strips in Real-Time
Ragab, K. (2021) · Lecture notes in networks and systems · doi:10.1007/978-3-030-82193-7_11 · Cited by 13
R-CNN-Based Large-Scale Object-Defect Inspection System for Laser Cutting in the Automotive Industry
Im, D., & Jeong, J. (2021) · Processes · doi:10.3390/pr9112043 · Cited by 12
“By comparison, for extracting features, such as the wavelet transform feature [9], the traditional machine-learning algorithm, such as the Support Vector Machine (SVM), has been studied for defect classification [9].”
MethodLü, P., Gao, B., Woo, W. L., Li, X., & Tian, G. Y. (2017) · IEEE Sensors Journal · doi:10.1109/jsen.2017.2722465 · Cited by 12
“[3] used imaging diagnostic system to automatic defect detection on hot-rolled steel surface, and revealed that three-level Haar feature set is more promising for defect detection.”
MethodXu, L., Tian, G., Zhang, L., & Zheng, X. (2019) · Chinese Automation Congress · doi:10.1109/cac48633.2019.8997452 · Cited by 13
“Santanu Ghorai proposed an automatic vision detection system with discrete wavelet transform (DWT)characteristics and support vector machine(SVM)[7].”
MethodAutomatic Metallic Surface Defect Detection using ShuffleDefectNet
Anvar, A., & Cho, Y. I. (2020) · Journal of the Korea Society of Computer and Information · doi:10.9708/jksci.2020.25.03.019 · Cited by 22
Surface defect classification of steel strip based on machine vision
Singhka, D. K. H., Neogi, N., & Mohanta, D. K. (2014) · doi:10.1109/iccct2.2014.7066698 · Cited by 13
“I. INTRODUCTION Steel strips are extensively used in industries and its surface quality is important for auto body, white goods and many other applications.”
BackgroundDetection Algorithm of Aluminum Surface Defects Using Machine Vision
Wu, Y., Liu, J., Zhang, Y., Yu, L., & Wu, J. (2019) · International Conference on Image, Video and Signal Processing (IVSP) · doi:10.1145/3317640.3317661 · Cited by 11
“Santanu [15] developed an automated visual inspection system (which localizes defects by employing kernel classifiers) for an integrated steel plant to capture surface images in real time.”
BackgroundLuo, Q., Liu, K., Su, J., Yang, C., Gui, W., Liu, L., & Sílven, O. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3098825 · Cited by 13
“utomated visual inspection (AVI) instrument plays an essential role for hot-rolled steel mills to ensure product quality [1] [2] [3].”
BackgroundACA-Net: An Adaptive Convolution and Anchor Network for Metallic Surface Defect Detection
Chen, F., Deng, M., Gao, H., Yang, X., & Zhang, D. (2022) · Applied Sciences · doi:10.3390/app12168070 · Cited by 11
Chu, M., Zhao, J., Gong, R., & Liu, L. (2017) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2017.7979072 · Cited by 11
“It can be seen that References [1-6] reckon steel surface defect as a single-label objective to study.”
BackgroundDetection of tyre defects using weighted quality-based convolutional neural network
Rajeswari, M., Julie, E. G., Robinson, Y. H., Joseph, E., Arun, A., Sebastian, E., Kumar, R., Long, H. V., & Sơn, L. H. (2022) · Soft Computing · doi:10.1007/s00500-022-06878-3 · Cited by 11
Three-dimensional defects detection of high-voltage cable joint based on iterative residual fitting
Zheng, Z., Bian, J., Gao, Y., He, S., Liu, W., Song, T., & Liu, G. (2022) · Measurement Science and Technology · doi:10.1088/1361-6501/aca116 · Cited by 10
A High-Quality Sample Generation Method for Improving Steel Surface Defect Inspection
He, Y., Li, S., Wen, X., & Xu, J. (2024) · Sensors · doi:10.3390/s24082642 · Cited by 11
“For instance, Ghorai et al. [14] extracted the set of wavelet features and then fed them into a SVM to identify surface defects.”
MethodSteel surface defects analysis with machine vision and deep learning
Frydrych, K., Tomczak, M., Jasinski, J. J., & Papanikolaou, S. (2025) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-025-16539-y · Cited by 15
“The application of the first type of approach was most often reported more than a decade ago, cf., e.g., [1, 15].”
Defect Detection Method For Steel Based On Semantic Segmentation
Zhou, G., & Sun, H. (2020) · IEEE Information Technology and Mechatronics Engineering Conference (ITOEC) · doi:10.1109/itoec49072.2020.9141596 · Cited by 10
“Although the artificial detection of steel defects has the advantages of high accuracy, it also has the following disadvantages: (1) long time; (2) easy to damage the surface; (3) high cost; For the first two problems, many solutions have been proposed, such as using scanning electron microscopy [22].”
BackgroundACRM: Attention Cascade R-CNN with Mix-NMS for Metallic Surface Defect Detection
Fang, J., Tan, X., & Wang, Y. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412424 · Cited by 13
“Traditional methods, including image processing methods [1] [2] and shallow machine learning methods [3], are commonly used.”
BackgroundMethodEnhanced You Only Look Once X for surface defect detection of strip steel
Wu, R., Zhou, F., Li, N., Liu, H., Guo, N., & Wang, R. (2022) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2022.1042780 · Cited by 12
“ASIS is a non-contact, non-destructive, and fully automated solution to complement or replace conventional detectors (Kapsalas et al., 2007; Ghorai et al., 2013; Xie et al., 2014; Kuo et al., 2018).”
BackgroundKang, D., Lai, J., & Yu, H. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.120121 · Cited by 13
Chaudhry, N. J., Khan, M. B., Iqbal, M. J., & Yasir, S. M. (2022) · Journal on artificial intelligence · doi:10.32604/jai.2022.038875 · Cited by 18
Process-monitoring-for-quality — A model selection criterion
Escobar, C. A., & Morales-Menéndez, R. (2018) · Manufacturing Letters · doi:10.1016/j.mfglet.2018.01.001 · Cited by 10
An adaptive feature refinement network for pixel-level segmentation of surface defect
Zhang, Y., Ge, W., Liu, S., Wang, J., Hu, H., Dong, J., & Zhang, T. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad9cb0 · Cited by 9
“…[7], wavelet transform [8, 9] and Gabor filters [10] in the frequency domain for defect segmentation, as well as some shallow learning-based detection models for defects classification, such as random forest [11, 12], support vector machine [13, 14], and shallow neural networks [15–17].”
Adaptive shape imitation and selective semantic guidance for industrial surface defect detection
Liang, X., Li, Y. Y., Wang, X., Liu, P., Shen, Y., & Guo, J. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127334 · Cited by 12
Liu, J., Zhang, Z., Alam, M. D. K., Cai, Q., Xia, C., & Tang, Y. (2025) · Digital Signal Processing · doi:10.1016/j.dsp.2025.105432 · Cited by 10
YOLO-DFW: An improved detection method for printed circuit board surface defects based on YOLOv8
Zhou, Y., Xu, X., Fan, W., & Jiang, Z. (2025) · Displays · doi:10.1016/j.displa.2025.103201 · Cited by 15
Steel surface defect detection algorithm based on improved YOLOv10
Zhang, L., Wang, Z., Ma, Y., & Li, G. (2025) · Scientific Reports · doi:10.1038/s41598-025-16725-8 · Cited by 15
Wibowo, A., Setiawan, J. D., Afrisal, H., Mahachandra, M., Santosa, S. P., Wisnu, K. B., Mardiyoto, A., Nurrakhman, H., Kartiwa, B., & Caesarendra, W. (2023) · Applied System Innovation · doi:10.3390/asi6010025 · Cited by 10
Luo, Q., He, H., Liu, K., Yang, C., Sílven, O., & Liu, L. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3265761 · Cited by 10
“in ensuring the quality of steel products [1], [2], [3].”
BackgroundGong, L., Dong, H., Zhang, X., Cheng, X., Ye, F., Guo, L., & Ge, Z. (2024) · Journal of Electronic Imaging · doi:10.1117/1.jei.33.3.033001 · Cited by 11
“15,16 However, as deep learning has advanced, the algorithms built on it have combined feature extraction and classification processes into a single composite operation to address surface defect detection issues in steel.”
BackgroundYuan, L., Chen, Y., Tang, H. R., Gao, R., & Wu, W. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3398769 · Cited by 13
“For instance, convolutional filters can be employed for smoothing and sharpening, Fourier transform can extract frequency domain features, and edge detection algorithms can identify boundaries within images [3], [4], [5], [6], [7], [8], [9], [10].”
MethodIntelligent vision based wear forecasting on surfaces of machine tool elements
Schlagenhauf, T., & Burghardt, N. (2021) · SN Applied Sciences · doi:10.1007/s42452-021-04839-3 · Cited by 10
“(Ghorai et al. 2013) present a somewhat earlier approach for the detection of defects on hot-rolled steel products which represents a better studied subfield for automatic flaw detection on metallic surfaces.”
BackgroundLearning a Class-specific and Shared Dictionary for Classifying Surface Defects of Steel Sheet
Zhou, S., Chen, Y., Zhang, D., Xie, J., & Zhou, Y. (2017) · ISIJ International · doi:10.2355/isijinternational.isijint-2016-478 · Cited by 9
Chen, H., Liu, J., Wang, S., & Liu, K. (2019) · IEEE Access · doi:10.1109/access.2019.2942218 · Cited by 9
“For non-textured surface images such as steel plate [6, 10], integrated circuit [11] or glass screen [12], statistics measures are widely employed [13] like first-order statistics (i.”
MethodHigh-Frequency Dual-Branch Network for Steel Small Defect Detection
Ma, C., Li, Z., Xue, Y., Li, S., & Sun, X. (2024) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-024-09352-4 · Cited by 8
Li, X., Zhao, Y., Zhao, Y., Guo, Z., Zhang, Y., Jiao, X., & Yuan, B. (2025) · PLoS ONE · doi:10.1371/journal.pone.0327139 · Cited by 11
Borwankar, R. M., & Ludwig, R. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.2990541 · Cited by 8
“These systems are seen in various industrial applications, including fabric inspection [3], aluminum and steel profiles inspection [4], [5], LCD, as well as railway track inspection [6], [7].”
BackgroundWavelet Subband-Based Tensor for Smartphone Physical Button Inspection
Giap, B. D., Le, N. T., Wang, J.-W., & Wang, C. (2021) · IEEE Access · doi:10.1109/access.2021.3099965 · Cited by 8
YOT-Net: YOLOv3 Combined Triplet Loss Network for Copper Elbow Surface Defect Detection
Xian, Y., Liu, G., Fan, J., Yu, Y., & Wang, Z. (2021) · Sensors · doi:10.3390/s21217260 · Cited by 8
“[15] utilizes a small set of wavelet features and employs support vector machine methods for defect detection.”
MethodSurface Defect Detection Using Deep U-Net Network Architectures
Üzen, H., Türkoğlu, M., & Hanbay, D. (2021) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu53274.2021.9477790 · Cited by 9
CS-YOLO-based cascaded detection method for paper cup defects
Wang, J., Xiong, Z., Peng, Z., & Xiang, Z. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/add6c5 · Cited by 7
“In the feature extraction phase, commonly used wavelet transforms (Ghorai et al 2012) and gradient-based information (Ren et al 2022) can extract key information from images.”
X-Ray Techniques for Defect Detection in Industrial Components and Materials: A Review
Wen, X., Chen, S., Song, K., Han, Y., Li, X., & Zhong, L. (2025) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2025.070906 · Cited by 7
“Infrared thermography and ultrasonic microscopy are suitable for the detection of material’s local microstructures [4].”
FMD-Framework: A Size Estimation Method for Pipeline Defects in Weld-Affected Zones
Zhang, X., Feng, J. Y., Lu, S., & Zhang, S. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3250239 · Cited by 7
“In [13], the statistical features of MFL measurements are analyzed, and a feature vector is constructed to deal with defect MFL signals.”
Efficient minor defects detection on steel surface via res-attention and position encoding
Wu, C., & He, T. (2024) · The Visual Computer · doi:10.1007/s00371-024-03583-0 · Cited by 10
Automated Machine Vision System for Inspecting Cutting Quality of Cubic Zirconia
Ekwongmunkong, W., Mittrapiyanuruk, P., & Kaewtrakulpong, P. (2016) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2016.2566858 · Cited by 7
An Improved GANs Model for Steel Plate Defect Detection
Tang, R., & Mao, K. (2020) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/790/1/012110 · Cited by 10
Deep Learning Framework for Steel Surface Defects Classification
Singari, R. M., Singla, K., & Chawla, G. (2019) · International Journal of Advanced Production and Industrial Engineering · doi:10.35121/ijapie201901135 · Cited by 7
Zhang, Z., Liu, W., Ostrosi, E., Tian, Y., & Yi, J. (2020) · Engineering Computations · doi:10.1108/ec-11-2019-0502 · Cited by 8
Defect Detection in Metal-Ceramic Substrate Based on Image Processing and Machine Learning
Zou, M., Matsunaga, K., Ueda, Y., Sugawara, T., Osanai, H., & Kageyama, Y. (2024) · IEEJ Journal of Industry Applications · doi:10.1541/ieejjia.23006878 · Cited by 12
“For instance, to perform defect classification, Song and Yan (5) improved the LBP method by combining it with an SVM. Based on wavelet features, Ghorai et al. (6) proposed an SVM to perform defect classification tasks.”
Online metallic surface defect detection using deep learning
ÇEREZCİ, F., Kazan, S., Öz, M. A. N., Öz, C., Taşcı, T., Hızal, S., & Altay, Ç. (2020) · Emerging Materials Research · doi:10.1680/jemmr.20.00197 · Cited by 7
Metadata
- Authors
- Ghorai, S., Mukherjee, A., Gangadaran, M., & Dutta, P. K.
- Affiliations
- Heritage Institute of Technology (IN)
- Indian Institute of Technology Kharagpur (IN)
- Steel Authority of India Limited (IN)
- Venue
- IEEE Transactions on Instrumentation and Measurement
- Published
- 2013-03
- Volume
- 62
- Issue
- 3
- Pages
- 612-621
- ISSN
- 0018-9456 (ISSN-L)
- 1557-9662
- OpenAlex
- W2078087367
- Cited by
- 317
- References
- 24
- Citations by year
- 2026: 13 · 2025: 26 · 2024: 46 · 2023: 46 · 2022: 36 · 2021: 23 · 2020: 33 · 2019: 25 · 2018: 22 · 2017: 17 · 2016: 12 · 2015: 8 · 2014: 5 · 2013: 5
- FWCI
- 14.16
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Instrumentation and Measurement (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
- automated defect detection, steel surface defects, wavelet features, Haar wavelet, Daubechies wavelet, multiwavelets, support vector machine, visual inspection system, defect localization, texture segmentation
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.