Automatic Metallic Surface Defect Detection and Recognition with Convolutional Neural Networks
Open accessThe DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index.
Abstract
Automatic metallic surface defect inspection has received increased attention in relation to the quality control of industrial products. Metallic defect detection is usually performed against complex industrial scenarios, presenting an interesting but challenging problem. Traditional methods are based on image processing or shallow machine learning techniques, but these can only detect defects under specific detection conditions, such as obvious defect contours with strong contrast and low noise, at certain scales, or under specific illumination conditions. This paper discusses the automatic detection of metallic defects with a twofold procedure that accurately localizes and classifies defects appearing in input images captured from real industrial environments. A novel cascaded autoencoder (CASAE) architecture is designed for segmenting and localizing defects. The cascading network transforms the input defect image into a pixel-wise prediction mask based on semantic segmentation. The defect regions of segmented results are classified into their specific classes via a compact convolutional neural network (CNN). Metallic defects under various conditions can be successfully detected using an industrial dataset. The experimental results demonstrate that this method meets the robustness and accuracy requirements for metallic defect detection. Meanwhile, it can also be extended to other detection applications.
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
Figures





![Figure 6 Segmentation results. The six rows are examples of defective images. ( a1 -a6 ) raw images, ( b1 -b6 ) results of Kittler [19], ( c1 -c6 ) results of Otsu [17], ( d1 -d6 ) results of a fully convolutional network (FCN) [36], ( e1 -e6 ) results of the cascaded autoencoder (CASAE) (proposed).](https://figures.cochat.ai/paper-figures/1442a57acfde49c0bea5ff40d56e9144/automatic-metallic-surface-defect-detection-and-recognition-with-convolutional-figure-6.png)



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.
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?
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Be of rotation and gray invariance, fast calculation speed.”
From Automated Visual Defect Classification for Flat Steel Surface: A Survey (2020) · cites this paper as [85]
Experimental — accuracy not yet measuredThe check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Sensitive to scale variation and noise interference.”
From Automated Visual Defect Classification for Flat Steel Surface: A Survey (2020) · cites this paper as [85]
Experimental — accuracy not yet measured
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“Our proposed CNN is a compact network that is smaller than the classic classification networks such as GoogleNet [41] and ResNet [42].”
MethodVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 1×
“We double the number of features after each max pooling layer in order to reduce the loss of semantic information [38,39].”
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
TensorFlow: A system for large-scale machine learning
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.08695 · Cited by 11,822
Rethinking Atrous Convolution for Semantic Image Segmentation
Chen, L.-C., Papandreou, G., Schroff, F., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1706.05587 · Cited by 7,517 · cited 1×
“In this paper, atrous convolution [40] is unitized to increase the receptive fields of the network for detecting large defects.”
MethodA survey of deep neural network architectures and their applications
Liu, W., Wang, Z., Liu, X., Zeng, N., Liu, Y., & Alsaadi, F. E. (2017) · Neurocomputing · doi:10.1016/j.neucom.2016.12.038 · Cited by 3,239 · cited 1×
“AE networks are widely used for information coding and reconstruction [37].”
BackgroundSelf-citationCha, Y., Choi, W., Suh, G., Mahmoudkhani, S., & Büyüköztürk, O. (2018) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.12334 · Cited by 1,558 · cited 1×
“[33] developed a structural damage detection method based on Faster R-CNN to detect five types of surface damages: concrete cracks, steel corrosion (medium and high levels), bolt corrosion, and steel delamination.”
MethodSong, K., & Yan, Y. (2013) · Applied Surface Science · doi:10.1016/j.apsusc.2013.09.002 · Cited by 1,026 · cited 2×
“These machine vision-based inspection systems occur in many industrial applications, such as steel strip inspection [2,3], liquid crystal display (LCD) inspection [4], fabric inspection [5,6], aluminum profiles [7], railway track inspection [8], food inspection [9], and optical components inspection [10].”
BackgroundImage deformation using moving least squares
Schaefer, S., McPhail, T., & Warren, J. (2006) · ACM Transactions on Graphics · doi:10.1145/1141911.1141920 · Cited by 674
Jia, F., Lei, Y., Lu, N., & Xing, S. (2018) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2018.03.025 · Cited by 587
Research works printed but not linked: 2
- 13. Tastimur, C.; Yetis, H.; Karaköse, M.; Akin, E. Rail defect detection and classification with real time image processing technique. Int. J. Comput. Sci. Softw. Eng. 2016 , 5 , 283.
- 19. Kalaiselvi, T.; Nagaraja, P. A rapid automatic brain tumor detection method for MRI images using modified minimum error thresholding technique. Int. J. Imaging Syst. Technol. 2015 , 1 , 77-85.
Cited by
Items 301–400 of 487
Convolutional Neural Networks Inference Memory Optimization with Receptive Field-Based Input Tiling
Zhuang, W., Hascoet, T., Chen, X., Takashima, R., Takiguchi, T., & Ariki, Y. (2023) · APSIPA Transactions on Signal and Information Processing · doi:10.1561/116.00000015 · Cited by 5
Trajectory prediction for heterogeneous road-agents using dual attention model
Zhao, S., Li, M., Huang, T., Li, S., & Xing, Z. (2023) · Measurement · doi:10.1016/j.measurement.2023.112685 · Cited by 5
Development of Image Processing Techniques in Crack Detection and Analysis
Dhafari, L. S. K. A., Afzal, A., Bahrani, R. I. A., Busaidi, Y. A., Sheikh-Akbari, A., & Hossain, S. (2023) · International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) · doi:10.1109/iceccme57830.2023.10252690 · Cited by 5
“last decade: (i) conventional visual examination based on image processing [3-5] and (ii) machine learning techniques [6, 7].”
BackgroundDeep Learning-Based Understanding of Defects in Continuous Casting Product
Ding, Z., Zhao, J., Misra, R. D. K., Guo, F., Xie, Z. J., Wang, X., Li, X., Wang, J., & Shang, C. (2023) · Metals · doi:10.3390/met13111809 · Cited by 4
“Tao et al. [19] designed a novel cascaded autoencoder architecture to segment and localize defects on a metallic surface.”
BackgroundDuarte, J., Claro, M. F., Vitoriano, P. M. A., Amaral, T. G., & Pires, V. F. (2025) · Eng—Advances in Engineering · doi:10.3390/eng6110302 · Cited by 4
“In [26], a cascaded autoencoder (CASAE) architecture was designed to segment and localize defects.”
Ricci curvature enhance the vision graph neural network for defect detection
Chen, Y., Huang, H., Lin, H., Hu, Y., Yan, Z., Hua, X., & Han, J. (2026) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-025-02781-4 · Cited by 4
A Novel Defect Detection Method for Ferrite Shield Surface Defects by Improved Faster R-CNN
Ye, X., Ye, J., He, Z., Zhang, D., Hu, X., & Chen, Q. (2022) · Scientific Programming · doi:10.1155/2022/5695243 · Cited by 3
“designed a cascaded autoencoder structure that introduced a semantic segmentation-based prediction mask and predicted the classifcation of segmentation results by convolution [6].”
MethodSelf-citationMachine Learning‐Based Automatic Scratch Performance Quantification on Polymeric Surfaces
Khatri, S., Li, Z., & Sue, H. (2025) · Journal of Applied Polymer Science · doi:10.1002/app.57456 · Cited by 3
Chmielowiec, A. (2025) · Lecture notes in mechanical engineering · doi:10.1007/978-3-031-94223-5_23 · Cited by 3
Polarimetric imaging for quality control in injection molding
Nagorny, P., Lacombe, T., Muller, T., Favrelière, H., Pairel, É., & Pillet, M. (2019) · International Conference on Quality Control by Artificial Vision (QCAV) · doi:10.1117/12.2522062 · Cited by 3
“Additional works on defects detection with Convolutional Neural Networks use Gaussian filtering.(33) In Figure 3 (c) & (d), we show the effect of a Sobel filter.”
MethodReal-time Fabric Defect Detection based on Lightweight Convolutional Neural Network
Liu, Z., Cui, J., Li, C., Ding, S., & Xu, Q. (2019) · International Conference on Computing and Pattern Recognition (ICCPR) · doi:10.1145/3373509.3373550 · Cited by 3
“More recently, [13, 14, 15] have adopted the deep learning technology to detect the fabric defect, and achieve the good detection results.”
BackgroundSemantic segmentation in flaw detection
Kotyuzanskiy, L. A., Ryzhkova, N. G., & Chetverkin, N. V. (2020) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/862/3/032056 · Cited by 3
“…i dentification of rock pore structures in scanning electron microscopy images to characterize the porosities [6]; generative adversarial network (GAN) model in a non-destructive testing system in thermography to detect defects in a carbon fiber reinforced polymer [7]; metallic defect detection [8].”
BackgroundOn study of a method for detecting micro-deformation defects of steel plate surface
Liu, X., He, Z., & Sun, Y. C. (2020) · doi:10.1117/12.2576393 · Cited by 3
“In Literature [6], it put forward an accurate measurement method for internal shape of large steel plates based on linear structured light scanning.6 It was able to measure internal depth information of steel plate, but was not accurate in defects detection of surface; what’s more, the light reflection on the steel pl…”
MethodInfluentialSelf-citationHuang, J., Sergin, N. D., Dua, A., Tavakoli, E. B., Yan, H., Ren, F., & Ju, F. (2020) · ASME International Manufacturing Science and Engineering Conference (MSEC) · doi:10.1115/msec2020-8261 · Cited by 3
“have applied CNNs for the metal surface image defect classification [20].”
MethodRail surface defect inspection via a self-reference template and similarity evaluation
Lang, N., Wang, D., Cheng, P., & Liu, L. (2021) · Measurement Science and Technology · doi:10.1088/1361-6501/ac31ca · Cited by 4
Automatic Detection of Weld Defects in Pressure Vessel X-Ray Image Based on CNN
Wenkai, X. I. A. O., Feng, X. Z., Shuiyu, N. A. N., & ZHANG, L. (2022) · Wuhan University Journal of Natural Sciences · doi:10.1051/wujns/2022276489 · Cited by 4
Machine Vision Inspection of Steel Surface Using Combined Global and Local Features
Ashour, M. W., Abdulrazzaq, M. M., & Siddique, M. (2023) · Advances in intelligent systems and computing · doi:10.1007/978-3-031-28332-1_41 · Cited by 4
Bernini, L., Albertelli, P., & Monno, M. (2023) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-023-11930-z · Cited by 3
Application of Machine Learning Algorithms in Cold-Rolled Strip Steel Surface Defect Grading Systems
Li, T., He, A., Kong, L., Zhang, M., Liu, C., Ma, X., & Xu, Y. (2023) · International Conference on Automation and Computing (ICAC) · doi:10.1109/icac57885.2023.10275297 · Cited by 4
“Furthermore, the development of deep learning technology has resulted in an increase in the number of studies in the field of surface inspection that use deep learning methods to detect defects [7,8].”
Benchmark: Formal Verification of Semantic Segmentation Neural Networks
Pal, N., Lee, S., & Johnson, T. T. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-46002-9_20 · Cited by 3
Li, S., & Li, C. (2023) · IEEE International Conference on Data Science and Computer Application (ICDSCA) · doi:10.1109/icdsca59871.2023.10393601 · Cited by 3
“Kang S et al.[2] proposed an improved ResNet feature extraction method in order to deal with the problem of defect detection of welding spot on steel plate surface, and the recall rate reaches 97%.”
MethodSetiawati, P., Karno, A. S. B., Hastomo, W., & Setiawan, I. (2024) · MALCOM Indonesian Journal of Machine Learning and Computer Science · doi:10.57152/malcom.v4i1.1258 · Cited by 3
AD3: Introducing a Score for Anomaly Detection Dataset Difficulty Assessment Using VIADUCT Dataset
Lehr, J., Philipps, J., Sargsyan, A., Pape, M., & Krüger, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73113-6_26 · Cited by 8
Apparatus and Method of Defect Detection for Resin Films
Sheu, R., Teng, Y.-H., Tseng, C.-H., & Chen, L.-C. (2020) · Applied Sciences · doi:10.3390/app10041206 · Cited by 3
“[33] designed a cascaded autoencoder architecture to obtain accurate and consistent defect detection results under complex lighting conditions and ambiguous defects.”
BackgroundA Lightweight Reconstruction Network for Surface Defect InspectionPreprint
Hu, C., Yao, J., Wu, W., Qiu, W., & Zhu, L. (2022) · Preprints.org · doi:10.20944/preprints202210.0355.v1 · Cited by 3
Tracking and Localization Method of Pipeline Pigs Based on a Noise Reduction Autoencoder
Guo, X., Song, H., Zeng, Y., Zheng, J., Fu, K., & Chen, H. (2023) · IEEE Access · doi:10.1109/access.2023.3240402 · Cited by 2
“In this paper, a denoising method for negative pressure wave signals of pigs based on a convolution self-coding neural network [11] is proposed.”
MethodYurov, V., Kuzenkov, S., & Цыганов, И. А. (2024) · International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency (SUMMA) · doi:10.1109/summa64428.2024.10803806 · Cited by 2
Liu, J., Li, H., Liu, H., & Liang, J. (2025) · International Journal of Cognitive Computing in Engineering · doi:10.1016/j.ijcce.2025.01.002 · Cited by 3
Realization of normal temperature detection through visible light images by Retinex-CNN
Zhu, J., He, Z., Huang, C., Zeng, J. H., Lin, H., Chen, F., Yu, C., Li, Y., Zhang, Y., Chen, H., et al. (2025) · Journal of Optics · doi:10.1007/s12596-025-02629-3 · Cited by 2
Redefining DMAIC With AI and Real-Time Data
Boopathy, G., Bose, G. C., Gayathri, M., & Kumar, M. H. (2025) · IGI Global eBooks · doi:10.4018/979-8-3373-0943-9.ch005 · Cited by 2
Huang, D., Xu, D., & Zhai, Y. (2026) · Sensors · doi:10.3390/s26041291 · Cited by 2
“YOLO models have been extensively applied in medical imaging [33,34], industrial manufacturing [35,36], agriculture and remote sensing [37,38], and autonomous driving [39,40].”
Self-citationPrieto-Sánchez, O. D., Morales-Cervantes, A., Téllez-Martínez, J. S., Chávez-Campos, G. M., Guevara, E., & Vergara-Hernández, H. J. (2026) · Materials · doi:10.3390/ma19050920 · Cited by 2
“In [16], a cascaded autoencoder architecture was implemented to identify damaged pixels and determine defect categories, achieving an accuracy of 89.6%, which meets the reliability and precision criteria for metal defect detection.”
InfluentialLiu, L., Mo, L., Zhao, S., He, M., (54296), L. C., & Chen, C. (2026) · International Journal of Pressure Vessels and Piping · doi:10.1016/j.ijpvp.2026.105907 · Cited by 2
Ting, Y.-C., Lin, D.-T., Chen, C.-F., & Tsai, B.-C. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-40605-9_31 · Cited by 2
Shi, Z., Xie, F., Huang, Z. R., Wang, B., Liu, Z., & Bai, S. (2021) · International Conference on Computer Information Science and Artificial Intelligence (CISAI) · doi:10.1109/cisai54367.2021.00024 · Cited by 2
A convolutional neural network method for damage location based on raw guided Lamb wave technique
Yu, S., Fan, C., Chen, Q., Gao, B., & Guo, J. (2021) · IEEE Far East NDT New Technology & Application Forum (FENDT) · doi:10.1109/fendt54151.2021.9749662 · Cited by 2
“In construction, industrial production, aerospace and other fields, some scholars have studied the application of ultrasonic nondestructive testing based on deep learning, Haixing Zhu studied the classification of welding surface defects based on deep learning, The defects were identified by convolutional neural netwo…”
BackgroundDigital Defect Simulation-based Data Generation for Visual Quality Inspection
Wang, X., Xie, Y., Zhang, Y., Pi, X., & Ren, F. (2023) · International Conference on Computer Modeling and Simulation (ICCMS) · doi:10.1145/3608251.3608291 · Cited by 2
“irreversible and may not fully coincide with real defects [13].”
BackgroundArm Injury Classification on a Small Custom Dataset Using CNNs and Augmentation
Nor’azam, A. F. B., & Mitani, Y. (2023) · International Conference on Computer Graphics and Image Processing (CGIP) · doi:10.1109/cgip58526.2023.00014 · Cited by 2
“The use of CNNs can be applied to any kind of images such as handwriting [13], object defects detection [14], malware detection [15], and medical images [16].”
BackgroundWan, Y., Zhang, L., Man, T., Ali, Z., & Zhou, H. (2024) · Optics and Lasers in Engineering · doi:10.1016/j.optlaseng.2024.108126 · Cited by 2
A Lightweight Reconstruction Network for Surface Defect Inspection
Hu, C., & Lai, S. (2023) · International Conference on Machine Vision, Image Processing and Imaging Technology (MVIPIT) · doi:10.1109/mvipit60427.2023.00013 · Cited by 2
Malashin, I. P., Kobernik, N. V., Панкратов, А. А., Andriyanov, Y. V., Aleksandrova, V. V., Тынченко, В. С., Nelyub, V., Бородулин, А. С., Gantimurov, A., Martysyuk, D., et al. (2024) · Metals · doi:10.3390/met14080929 · Cited by 2
“Tao et al.’s [47] paper introduces a novel cascaded autoencoder (CASAE) architecture for robust defect detection.”
BackgroundYang, X., Tan, H., & Wang, X. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72356-8_19 · Cited by 2
Comparison of Various Feature Extractors and Classifiers in Wood Defect Detection
KILIÇ, K., Kılıç, K., Doğru, İ. A., & Özcan, U. (2025) · Drvna industrija · doi:10.5552/drvind.2025.0217 · Cited by 2
Machine Learning approach for Defect Identification in Machinery parts
Abin, D., Solanki, M., Waghchaure, N., Shivthare, S., & Augustine, R. (2019) · IEEE Bombay Section Signature Conference (IBSSC) · doi:10.1109/ibssc47189.2019.8973021 · Cited by 2
“Xian Tao et al in “Automatic Metallic Surface Defect Detection and Recognition with Convolutional Neural Networks”, states a metallic defect detection inspection system which is automated and consists of a two-fold procedure including a defect detection module called CASAE (cascaded autoencoder) and a classification m…”
MethodQuality control automation of metallic surface using machine vision
Lenty, B., & Kwiek, P. J. (2021) · Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments (WILGA) · doi:10.1117/12.2613807 · Cited by 2
Detecting aluminium tube surface defects by using faster region-based convolutional neural networks
Chen, S., Wang, D.-G., & Wang, F.-B. (2022) · Journal of Computational Methods in Sciences and Engineering · doi:10.3233/jcm-226107 · Cited by 2
CNN-based Asymmetric Detection Method for Appearance Inspection
Okazaki, M., & Hanayama, R. (2022) · Journal of the Japan Society for Precision Engineering · doi:10.2493/jjspe.88.703 · Cited by 2
A Deep Learning Based End-to-end Surface Defect Detection Method for Industrial Scenes
Lan, Y., & Huang, C. (2023) · International Conference on Bioinformatics and Intelligent Computing (BIC) · doi:10.1145/3592686.3592695 · Cited by 2
“Faster-RCNN(Res-50) [13] 72.75% Uninf.stud [20] 83.5% CASAE [10] 89.02% MS.method [18] 91.6% CNSDF (Ours) 93.9% with the number of training rounds, 𝑛 refers to the current number of training rounds, and 𝑛 𝑒𝑝 is the total number of training rounds.”
BackgroundMethodInfluentialAnalysis of Submerged Arc Welding (SAW) Surface Defects Using Convolutional Neural Network (CNN)
FarhatullaBaig, M., Adamsab, K., & Dubey, D. K. (2023) · Lecture notes in mechanical engineering · doi:10.1007/978-981-99-1308-4_23 · Cited by 2
Toward Fault Detection in Industrial Welding Processes with Deep Learning and Data AugmentationPreprint
Antony, J., Schlather, F., Safronov, G. S., Schmitz, M., & Laerhoven, K. V. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.10160 · Cited by 2
“Another novel cascaded autoencoder network for the segmentation and localization of the defects on the defect localization on metallic surfaces is developed by [10], where their model could generate a prediction mask over the failures.”
BackgroundKlarák, J., Klačková, I., Andok, R., Hricko, J., Bulej, V., & Tsai, H. (2023) · Sensors · doi:10.3390/s23104772 · Cited by 1
“The work [22] describes the method of finding anomalies in visual content through the cascaded autoencoder (CASAE) architecture based on two levels of autoencoder.”
MethodSurface Defect Detection Algorithm of Aluminum Sheet Based on Improved Yolov3
Liu, Y., Hu, G., & Huang, L. (2023) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-32443-7_9 · Cited by 1
Sandhu, M. A., Amin, A., Tariq, S., & Mehmood, S. (2023) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-233292 · Cited by 1
“Theapplicationsofsemanticsegmenta-tionspanvariousreal-worlddomains,including pedestrian detection [16], defect detection [17], self-driving vehicles [18], and computer-aided diagnosis.”
Surface Defect Detection of Mining Automation Equipment Based on Convolutional Neural Networks
Bian, Z. (2024) · Applied Mathematics and Nonlinear Sciences · doi:10.2478/amns-2024-3500 · Cited by 1
Realising Quality Control of Metal Products Used in Industry Through Deep Learning
Özyer, B., & Taşpınar, Y. S. (2024) · Intelligent Methods in Engineering Sciences · doi:10.58190/imiens.2024.114 · Cited by 1
Microsurface Defect Recognition via Microlaser Line Projection and Affine Moment Invariants
Rodríguez, J. A. M. (2025) · Coatings · doi:10.3390/coatings15040385 · Cited by 1
Image-Based Machine Learning Methods in Materials Microstructure and Failure Analysis
Akbari, M., Wang, A. Y.-D., Wang, Q. G., & Yan, C. (2025) · SAE technical papers on CD-ROM/SAE technical paper series · doi:10.4271/2025-01-8324 · Cited by 1
Modular Anti-noise Deep Learning Network for Robotic Grasp Detection Based on RGB Images
Li, Z., & Zhong, J. (2024) · International Conference on Electronics and Electrical Engineering Technology (EEET) · doi:10.1109/eeet64351.2024.00022 · Cited by 1
“…autonomous driving scenarios; Flohr et al. [24] present an iterative framework for achieving highly accurate pedestrian segmentation; Tao et al. [25] propose a cascading network which transforms the input defect image into a pixel-wise prediction mask to detect metallic defects, being based on…”
Metal Surface Defect Detection Based on Transformer Merging Edge Information
Ling, J., Tan, C., & Cui, L. (2025) · International Symposium on System Security, Safety, and Reliability (ISSSR) · doi:10.1109/isssr65654.2025.00024 · Cited by 1
Enhanced crack detection in large stamped metal products via deep learning and edge line analysis
Zhang, P., Kong, Y., & Park, G. (2025) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-025-16226-y · Cited by 1
“To enable defect localization, Su et al. [10] proposed a cascaded model combining ResNet [11] and YOLOv3 [12], and Tao et al. [13] introduced a cascaded autoencoder structure to localize defects on metal surfaces.”
A lightweight network for weak texture surface defect detection
Peng, L., Lv, B., Gao, X., Liu, H., Huang, G., & Yu, Z. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.113554 · Cited by 1
Yin, Z., Zhang, L., Liu, H., Du, Q., & Yu, C. (2026) · Frontiers in Computer Science · doi:10.3389/fcomp.2025.1700167 · Cited by 1
“Tao et al. (2018) proposed a deep convolutional neural network cascade autoencoder (CASAE) for segmenting and positioning surface defects, addressing the problem of metal surface defect detection in complex industrial scenarios.”
Xu, X., Li, Y., He, W., Yang, S., Wang, C., & Wang, S. (2026) · Tunnelling and Underground Space Technology · doi:10.1016/j.tust.2026.107502 · Cited by 1
Development & characterization of electrodes for large-scale Xenon Time Projection Chambers
Elykov, A., Vetter, S., Wu, V. H. S., Deisting, A., Eitel, K., Gumbsheimer, R., Kara, M., Lichter, S., Lindemann, S., Luce, T. C., et al. (2026) · Journal of Instrumentation · doi:10.1088/1748-0221/21/02/p02035 · Cited by 1
Hu, X., Zhou, N., Luan, F., Wu, Z., & Yang, J. (2026) · Journal of Energy Storage · doi:10.1016/j.est.2026.121642 · Cited by 1
Lee, H. G., Kim, Y., Choi, H. J., Jeong, D., Kim, J., Ryu, D. Y., Kim, Y., & Ahn, H. (2026) · Photon Science · doi:10.1021/photonsci.6c00010 · Cited by 1
Color Based Image Processing Techniques to Detect Oxide Film during Welding
Gupta, S. S., Kwon, T.-H., & Kim, K. (2020) · International Conference on Electronics, Information, and Communication (ICEIC) · doi:10.1109/iceic49074.2020.9051365 · Cited by 1
“[14] proposed a method which can detect and classify any surface defect.”
MethodVisual inspection for metallic surfaces: CNN driven by features
Fantinel, R., & Cenedese, A. (2019) · International Conference on Quality Control by Artificial Vision (QCAV) · doi:10.1117/12.2521455 · Cited by 1
Defect Detection of Production Surface Based on CNN
Sun, Y., Cai, Y., Li, Y., & Zhao, Y. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-64243-3_30 · Cited by 1
A Lightweight and Efficient Network for Logistics Truck Scene Semantic Segmentation
Liu, S., Li, B., Xiong, J., Wang, F., Zhuo, Z., & Ren, X. (2020) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc51575.2020.9345246 · Cited by 1
“A number of researchers are struggling in this area to timely provide solutions for meeting the industrial requirement [3]–[5].”
BackgroundInfluence of Longitudinal Scratch Defects on the Bendability of Titanium Alloy
Kwame, J. (2021) · Journal of Material Sciences & Manfacturing Research · doi:10.47363/jmsmr/2021(2)116 · Cited by 1
Complex Product Displaced and Missing Assembly Detection Based on Vision and Process Template
Lv, N., Du, F., & Wang, Y. W. (2021) · International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE) · doi:10.1109/aemcse51986.2021.00255 · Cited by 1
Surface Defect Detection Model of Motor Commutator Based on Semantic Segmentation
Hu, S. (2021) · Journal of Engineering Mechanics and Machinery · doi:10.23977/jemm.2021.060110 · Cited by 1
“[1] proposed a novel cascaded autoencoder to accurately locate and classify defects appearing in images captured from real industrial environments.”
BackgroundAutomated Shell Abrasion Detection for Cell Phone Based on GraphFPN With Learnable Sparse Priors
Wu, H., Guo, X., Xiao, F., Yan, W., & Wen, Z. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3150591 · Cited by 2
Wiper Arm Defect Detection Using Laplacian Pyramids and Genetic Algorithm
Ler, W. X., Tay, L. C., & Goh, K. M. (2022) · IEEE International Colloquium on Signal Processing & Its Applications (CSPA) · doi:10.1109/cspa55076.2022.9782024 · Cited by 1
“Xian Tao et al [21] worked on an automatic defect detection and inspection on metallic surface based on Cascade Auto-encoder (CASAE).”
MethodBanf, M., & Steinhagen, G. (2022) · Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science · doi:10.11159/mhci22.104 · Cited by 1
“Accordingly, a plethora of machine learning based condition monitoring and workpiece inspection methodologies and applications have been proposed, including gearbox [1] or rotary machinery analyses [2], as well as bearing [3, 4] or steel surface defect detection [5-10], just to name a few.”
BackgroundDefect Detection in Multiple Product Variants Using Hammering Test with Machine Learning
Yamashita, Y., Yoshida, K., Kishita, Y., & Umeda, Y. (2022) · International Journal of Automation Technology · doi:10.20965/ijat.2022.p0783 · Cited by 1
Self-supervised and Template-Enhanced Unknown-Defect Detection
Li, T., Liao, Y., Wang, X., Kuang, G., Chen, Z., & Yang, J. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-18913-5_57 · Cited by 1
Surface Defect Detection of Aluminum Material based on Deep Learning
Li, T., Xing, L., Fan, H., & Zhu, H. (2022) · IEEE International Conference on Advances in Electrical Engineering and Computer Applications (AEECA) · doi:10.1109/aeeca55500.2022.9919026 · Cited by 1
“In the industrial field, many scholars try to use deep learning methods to detect surface defects in the production process of castings, trying to find an effective detection algorithm to improve the speed and accuracy of casting inspections and save production costs [4].”
BackgroundDefect Recognition of Metal Components Based On Transfer Learning and Feature Fusion
Li, Y., Junren, Z., Hailong, L., & Chen, X. (2022) · International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP) · doi:10.1109/iccwamtip56608.2022.10016502 · Cited by 1
“Tao et al. [8]proposed an automatic method to detect defects on metallic surfaces as well as a method based on the CNN by using a cascaded autoencoder to segment and localize the defects.”
MethodCotton Packaging Defect Detection Based on Improved SVM Algorithm
Bowen, Z., Lu, H., & Xiuyun, Z. (2022) · World Conference on Mechanical Engineering and Intelligent Manufacturing (WCMEIM) · doi:10.1109/wcmeim56910.2022.10021478 · Cited by 1
“The key of defect detection based on SVM was how to extract a great defect feature and further design of defect classifier, because the texture of the cotton packaging studied in this paper was more complex, so extracted the defect feature of the texture feature in this paper, and analyzed the following three gray sca…”
MethodA Convolution Neural Network-based Approach for Metal Surface Roughness Evaluation
Pan, Z., Liu, Y. H., Li, Z., Xun, Q., & Wu, Y. (2023) · Current Materials Science · doi:10.2174/2666145416666230420093435 · Cited by 1
Research of Neural Network Methods of Visual Defectoscopy of Metal Structures
Chernikov, A., Smirnova, E., & Zhavoronkov, O. (2023) · International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM) · doi:10.1109/icieam57311.2023.10139006 · Cited by 1
“This method has also found application for the search for defects in metallurgy under certain specific conditions [26][27].”
MethodDefect Detection in Batavia Woven Fabrics by Means of Convolutional Neural Networks
Velasco-Pérez, N., Lozano-Juárez, S., Gil-Arroyo, B., Sanz, J. M., Basurto, N., Urda, D., & Herrero, Á. (2023) · Lecture notes in networks and systems · doi:10.1007/978-3-031-42536-3_20 · Cited by 1
Reinforcement learning-based approach for plastic texture surface defects inspection
Ho, C.-C., Chiao, Y.-C., & Su, E. (2023) · The Visual Computer · doi:10.1007/s00371-023-03077-5 · Cited by 1
“AOI is classified as traditional optical inspection or deep learning auxiliary optical inspection [1–3].”
Robotic Slag Removal System with Position Compensation and Defect Detection based on YOLO Algorithm
Shih, C.-H., & Wu, C.-Y. (2023) · International Conference on Advanced Robotics and Intelligent Systems (ARIS) · doi:10.1109/aris59192.2023.10268517 · Cited by 1
DETECTION OF ANOMALIES ON THE SURFACE OF WORKPIECES PRODUCED ON CNC MACHINES
Ilić, V., & Medojević, M. (2023) · International Scientific Conference on Industrial Systems (IS) · doi:10.24867/is-2023-t3.1-2_11141 · Cited by 1
Kyriakides, G., & Daskalakis, A. (2023) · OALib · doi:10.4236/oalib.1110833 · Cited by 1
Botejara-Antúnez, M., González‐Domínguez, J., Sánchez‐Barroso, G., & García‐Sanz‐Calcedo, J. (2023) · Architectural Engineering and Design Management · doi:10.1080/17452007.2023.2291586 · Cited by 1
“Tao, Zhang, Ma, Liu, and Xu (2018) designed a novel ‘Cascaded Autoencoder’ architecture based on a convolutional neural network (CNN) to segment and locate defects and pathologies.”
Development of an Autonomous Unmanned Aerial Vehicle for Rapid Aircraft Defect Detection
Hossain, S., Afzal, A., Dhafari, L. S. K. A., AlManai, A., & Bahrani, R. I. A. (2023) · Springer eBooks · doi:10.1007/978-981-99-7775-8_9 · Cited by 1
Automatic Detection of Defective Metal Pressed Components Using Artificial Intelligence
Aharari, A., Inaba, K., & Mehdipour, F. (2023) · International Conference on Circuits, Systems, Communications and Computers (CSCC) · doi:10.1109/cscc58962.2023.00011 · Cited by 1
Multi-Modal Defect Detection System for Single Color Fabrics in the Apparel Industry
Silva, V. D., Senevirathne, T., Fareed, N., Sandanayake, T. C., & Karunaratne, I. (2023) · International Conference on Information Technology Research (ICITR) · doi:10.1109/icitr61062.2023.10382928 · Cited by 1
“Existing research indicates that undetected fabric defects during manual quality checks can lead to a significant decrease of up to 65% in the selling price of ready-made garments [2].”
BackgroundRegistration Based Feature Core-Set Model for Defect Detection
Jing, X. (2023) · China Automation Congress (CAC) · doi:10.1109/cac59555.2023.10450867 · Cited by 1
“Defect detection is the process of using computer vision technologies to detect and locate defects in the target, which has broad industrial applications, such as metal defect detection [1] and electronic component defect detection [2].”
MethodHigh Precision Ultrasonic Testing Method for Density of Engineering Plastics
Li, C., Wang, L., Sun, L., Chu, Z., Liu, W., & Tao, J. (2024) · Russian Journal of Nondestructive Testing · doi:10.1134/s1061830924600011 · Cited by 1
“It is challenging to derive a robust regression model [27, 28], making it difficult to meet the precision requirements for on-site engineering testing.”
Guo, J., Han, C., Ma, Y., & Zhang, C. (2024) · IISE Transactions · doi:10.1080/24725854.2024.2425292 · Cited by 2
“Additionally, DNNs can compile these two tasks into one model for parameter optimization (Tao et al ., 2018; Han et al ., 2020; Tabernik et al ., 2020).”
Tan, Y., Banerjee, B., & Ranjan, R. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-80136-5_2 · Cited by 1
U-Shape Network for Chip Surface Defect Detection
Ruan, R., Zou, W., Li, Z., Qin, Z., Wu, Q., & Huang, S. (2024) · IEEE International Conference on e-Business Engineering (ICEBE) · doi:10.1109/icebe62490.2024.00053 · Cited by 1
“Some supervised learning methods use datasets including DAGM2007, road crack datasets [1], railway datasets [2], fabric datasets [3], silicon steel strip datasets [4], and railway defect datasets [5].”
Fantinel, R., & Cenedese, A. (2020) · Journal of Electronic Imaging · doi:10.1117/1.jei.29.4.041005 · Cited by 1
“In the specialized literature, crack detection applications, based on both machine learning (ML) 14 – 16 and deep learning (DL), 17,18 are usually applied to static images.”
BackgroundGAN based ball screw drive picture database enlargement for failure classificationPreprint
Schlagenhauf, T., Sun, C., & Fleischer, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.10235 · Cited by 1
“In the field of surface failure classification, [19] did metallic surface failure detection and enlarge the failure image dataset using classical data augmentation.”
BackgroundBruce, D., Sanghvi, H. A., & Agarwal, A. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4517717 · Cited by 1
Metadata
- Authors
- Tao, X., Zhang, D., Ma, W., Liu, X., & Xu, D.
- Affiliations
- Chinese Academy of Sciences (CN)
- China University of Mining and Technology - Beijing (CN)
- Corresponding author
- Tao, Xian
- Venue
- Applied Sciences
- Publisher
- MDPI AG
- Published
- 2018-09-06
- Volume
- 8
- Issue
- 9
- Pages
- 1575
- ISSN
- 2076-3417 (ISSN-L)
- OpenAlex
- W2890747436
- Semantic Scholar
- 10447a2738ff7ac47f8d93c85222ee737412cf53
- Cited by
- 471
- References
- 43
- Citations by year
- 2026: 29 · 2025: 42 · 2024: 60 · 2023: 94 · 2022: 72 · 2021: 82 · 2020: 58 · 2019: 32 · 2018: 2
- FWCI
- 36.08
- Type
- journal article
- Language
- en
- Open access
- gold
- dx.doi.org
- Licence
- Locations
- Applied Sciences (publishedVersion, cc-by)
- ELARTU (Ternopil National Technical University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Natural Science Foundation of China (61703399, 61503376, 61673383)
- 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 localization, defect classification, semantic segmentation, convolutional neural networks, manufacturing quality control, industrial inspection
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.