Solid Surfaces, Defects and Detection

A special issue of Coatings (ISSN 2079-6412). This special issue belongs to the section "Surface Characterization, Deposition and Modification".

Deadline for manuscript submissions: closed (20 December 2023) | Viewed by 17178

Special Issue Editor

School of Mechanical Engineering & Automation, Northeastern University, Shenyang 110819, China
Interests: applied surface science; vision detection for surface defects; multi-modal image analysis and application
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

As an important application of coatings, solid surface has been widely used in various industrial coating fields. Due to problems of material properties and process flow, the solid surface will inevitably produce many defects, such as cracks and shrinkage holes. These defects seriously affect the quality of products; therefore, timely detection is needed.

Accordingly, we have launched this new Special Issue of Coatings, which will collect original research articles and review papers focusing on the fundamentals and application of applied surface science and engineering for coatings. We invite papers dealing with, but not limited to, the following topics: coatings for solid surfaces, theoretical and computational modeling of solid surfaces, vision detection for surface defects, artificial intelligence of vision detection, recognition of industrial products, hidden defect detection and classification methods, non-destructive testing and evaluation using image processing methods.

We look forward to receiving your contribution.

Prof. Dr. Kechen Song
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Coatings is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • coatings for solid surfaces
  • vision detection for surface defects
  • defect classification
  • artificial intelligence of vision detection
  • non-destructive testing

Published Papers (10 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review

14 pages, 3141 KiB  
Article
Low-Resolution Steel Surface Defects Classification Network Based on Autocorrelation Semantic Enhancement
by Xiaoe Guo, Ke Gong and Chunyue Lu
Coatings 2023, 13(12), 2015; https://doi.org/10.3390/coatings13122015 - 28 Nov 2023
Viewed by 588
Abstract
Aiming at the problems of low-resolution steel surface defects imaging, such as defect type confusion, feature blurring, and low classification accuracy, this paper proposes an autocorrelation semantic enhancement network (ASENet) for the classification of steel surface defects. It mainly consists of a backbone [...] Read more.
Aiming at the problems of low-resolution steel surface defects imaging, such as defect type confusion, feature blurring, and low classification accuracy, this paper proposes an autocorrelation semantic enhancement network (ASENet) for the classification of steel surface defects. It mainly consists of a backbone network and an autocorrelation semantic enhancement module (ASE), in which the autocorrelation semantic enhancement module consists of three main learnable modules: the CS attention module, the autocorrelation computation module, and the contextual feature awareness module. Specifically, we first use the backbone network to extract the basic features of the image and then use the designed CS attention module to enhance the basic features. In addition, to capture different aspects of semantic objects, we use the autocorrelation module to compute the correlation between neighborhoods and contextualize the basic and augmented features to enhance the recognizability of the features. Experimental results show that our method produces significant results, and the classification accuracy reaches 96.24% on the NEU-CLS-64 dataset. Compared with ViT-B/16, Swin_t, ResNet50, Mobilenet_v3_small, Densenet121, Efficientnet_b2, and baseline, the accuracy is 9.43%, 5.15%, 4.87%, 3.34%, 3.28%, 3.01%, and 2.72% higher, respectively. Full article
(This article belongs to the Special Issue Solid Surfaces, Defects and Detection)
Show Figures

Figure 1

19 pages, 4047 KiB  
Article
WFRE-YOLOv8s: A New Type of Defect Detector for Steel Surfaces
by Yao Huang, Wenzhu Tan, Liu Li and Lijuan Wu
Coatings 2023, 13(12), 2011; https://doi.org/10.3390/coatings13122011 - 28 Nov 2023
Cited by 1 | Viewed by 1124
Abstract
During the production of steel, in view of the manufacturing engineering, transportation, and other factors, a steel surface may produce some defects, which will endanger the service life and performance of the steel. Therefore, the detection of defects on a steel surface is [...] Read more.
During the production of steel, in view of the manufacturing engineering, transportation, and other factors, a steel surface may produce some defects, which will endanger the service life and performance of the steel. Therefore, the detection of defects on a steel surface is one of the indispensable links in production. The traditional defect detection methods have trouble in meeting the requirements of high detection accuracy and detection efficiency. Therefore, we propose the WFRE-YOLOv8s, based on YOLOv8s, for detecting steel surface defects. Firstly, we change the loss function to WIoU to address quality imbalances between data. Secondly, we newly designed the CFN in the backbone to replace C2f to reduce the number of parameters and FLOPs of the network. Thirdly, we utilized RFN to complete a new neck RFN to reduce the computational overhead and, at the same time, to fuse different scale features well. Finally, we incorporate the EMA attention module into the backbone to enhance the extraction of valuable features and improve the detection accuracy of the model. Extensive experiments are carried out on the NEU-DET to prove the validity of the designed module and model. The mAP0.5 of our proposed model reaches 79.4%, which is 4.7% higher than that of YOLOv8s. Full article
(This article belongs to the Special Issue Solid Surfaces, Defects and Detection)
Show Figures

Figure 1

14 pages, 1791 KiB  
Article
Multi-Scale Lightweight Neural Network for Steel Surface Defect Detection
by Yichuan Shao, Shuo Fan, Haijing Sun, Zhenyu Tan, Ying Cai, Can Zhang and Le Zhang
Coatings 2023, 13(7), 1202; https://doi.org/10.3390/coatings13071202 - 04 Jul 2023
Cited by 2 | Viewed by 1060
Abstract
Defect classification is an important aspect of steel surface defect detection. Traditional approaches for steel surface defect classification employ convolutional neural networks (CNNs) to improve accuracy, typically by increasing network depth and parameter count. However, this approach overlooks the significant memory overhead of [...] Read more.
Defect classification is an important aspect of steel surface defect detection. Traditional approaches for steel surface defect classification employ convolutional neural networks (CNNs) to improve accuracy, typically by increasing network depth and parameter count. However, this approach overlooks the significant memory overhead of large models, and the incremental gains in accuracy diminish as the number of parameters increases. To address these issues, a multi-scale lightweight neural network model (MM) is proposed. The MM model, with a fusion encoding module as its core, constructs a multi-scale neural network by utilizing the Gaussian difference pyramid. This approach enhances the network’s ability to capture patterns at different resolutions while achieving superior model accuracy and efficiency. Experimental results on a dataset from a hot-rolled strip steel plant demonstrate that the MM network achieves a classification accuracy of 98.06% in defect classification tasks. Compared to networks such as ResNet-50, ResNet-101, VGG, AlexNet, MobileNetV2, and MobileNetV3, the MM model not only reduces the number of model parameters and compresses model size but also achieves better classification accuracy. Full article
(This article belongs to the Special Issue Solid Surfaces, Defects and Detection)
Show Figures

Figure 1

10 pages, 2085 KiB  
Article
A Distribution-Preserving Under-Sampling Method for Imbalance Defect Recognition in Castings
by Han Yu, Xinyue Li, Xingjie Li, Chunyu Hou, Shangyu Liu and Huasheng Xie
Coatings 2022, 12(12), 1808; https://doi.org/10.3390/coatings12121808 - 24 Nov 2022
Viewed by 920
Abstract
Data imbalance is a crucial factor that limits the performance of automatic defect recognition systems in castings. The bias and deterioration of the model are generated by massive normal samples and minor defect samples. Traditional re-sampling methods randomly change the data distribution and [...] Read more.
Data imbalance is a crucial factor that limits the performance of automatic defect recognition systems in castings. The bias and deterioration of the model are generated by massive normal samples and minor defect samples. Traditional re-sampling methods randomly change the data distribution and ignore the significant intra-class difference among all normal samples. Therefore, this paper proposes a distribution-preserving under-sampling method for imbalance defect-recognition in castings. In detail, our method divides all normal samples into several sub-groups by cluster analysis and reassembles them into some balance datasets, which makes the normal samples in all balance datasets have an identical distribution with the original imbalance dataset. Finally, experiments on our dataset with 3260 images indicate that the proposed method achieves a 0.816 AUC (area under curve) score, which demonstrates significant advantages compared to cost-sensitive learning and re-sampling methods. Full article
(This article belongs to the Special Issue Solid Surfaces, Defects and Detection)
Show Figures

Figure 1

16 pages, 4850 KiB  
Article
TSSTNet: A Two-Stream Swin Transformer Network for Salient Object Detection of No-Service Rail Surface Defects
by Chi Wan, Shuai Ma and Kechen Song
Coatings 2022, 12(11), 1730; https://doi.org/10.3390/coatings12111730 - 12 Nov 2022
Cited by 8 | Viewed by 1520
Abstract
The detection of no-service rail surface defects is important in the rail manufacturing process. Detection of defects can prevent significant financial losses. However, the texture and form of the defects are often very similar to the background, which makes them difficult for the [...] Read more.
The detection of no-service rail surface defects is important in the rail manufacturing process. Detection of defects can prevent significant financial losses. However, the texture and form of the defects are often very similar to the background, which makes them difficult for the human eye to distinguish. How to accurately identify rail surface defects thus poses a challenge. We introduce salient object detection through machine vision to deal with this challenge. Salient object detection locates the most “significant” areas of an image using algorithms, which constitute an integral part of machine vision inspection. However, existing saliency detection networks suffer from inaccurate positioning, poor contouring, and incomplete detection. Therefore, we propose an innovative deep learning network named Two-Stream Swin Transformer Network (TSSTNet) for salient detection of no-service rail surface defects. Specifically, we propose a two-stream encoder—one stream for feature extraction and the other for edge extraction. TSSTNet also includes a three-stream decoder, consisting of a saliency stream, edge stream, and fusion stream. For the problem of incomplete detection, we innovatively introduce the Swin Transformer to model global information. For the problem of unclear contours, we expect to deepen the understanding of the difference in depth between the foreground and background through the learning of contour maps, so the contour alignment module (CAM) is created to deal with this problem. Moreover, to make the most of multimodal information, we suggest a multi-feature fusion module (MFFM). Finally, we conducted comparative experiments with 10 state-of-the-art (SOTA) approaches on the NRSD-MN datasets, and our model performed more competitively than others on five metrics. Full article
(This article belongs to the Special Issue Solid Surfaces, Defects and Detection)
Show Figures

Figure 1

14 pages, 3020 KiB  
Article
A Semi-Supervised Inspection Approach of Textured Surface Defects under Limited Labeled Samples
by Yu He, Xin Wen and Jing Xu
Coatings 2022, 12(11), 1707; https://doi.org/10.3390/coatings12111707 - 09 Nov 2022
Cited by 4 | Viewed by 1222
Abstract
Defect inspection is a key step in guaranteeing the surface quality of industrial products. Based on deep learning (DL) techniques, related methods are highly effective in defect classification tasks via a supervision process. However, collecting and labeling many defect samples are usually harsh [...] Read more.
Defect inspection is a key step in guaranteeing the surface quality of industrial products. Based on deep learning (DL) techniques, related methods are highly effective in defect classification tasks via a supervision process. However, collecting and labeling many defect samples are usually harsh and time-consuming processes, limiting the application of these supervised classifiers on various textured surfaces. This study proposes a semi-supervised framework, based on a generative adversarial network (GAN) and a convolutional neural network (CNN), to classify defects of a textured surface, while a novel label assignment scheme is proposed to integrate unlabeled samples into semi-supervised learning to enhance the overall performance of the system. In this framework, a customized GAN uses limited labeled samples to generate unlabeled ones, while the proposed label assignment scheme makes the generated data follow different label distributions in such a way that they can participate in training with labeled data. Finally, a CNN is proposed for semi-supervised training and the category identification of each defect sample. Experimental results show the effectiveness and robustness of the proposed framework even if original samples are limited. We verify our approach on four different surface defect datasets, achieving consistently competitive performances. Full article
(This article belongs to the Special Issue Solid Surfaces, Defects and Detection)
Show Figures

Figure 1

17 pages, 35581 KiB  
Article
A Novel Sub-Pixel-Shift-Based High-Resolution X-ray Flat Panel Detector
by Jiayin Liu and Jae Ho Kim
Coatings 2022, 12(7), 921; https://doi.org/10.3390/coatings12070921 - 29 Jun 2022
Cited by 1 | Viewed by 1861
Abstract
In this paper, we describe a novel sub-pixel shift (SPS)-based X-ray flat panel detector (FPD), which can achieve high resolution while maintaining a high SNR (signal-to-noise ratio). In the proposed architecture, an XY precision shift stage is applied to complete the sub-pixel shift [...] Read more.
In this paper, we describe a novel sub-pixel shift (SPS)-based X-ray flat panel detector (FPD), which can achieve high resolution while maintaining a high SNR (signal-to-noise ratio). In the proposed architecture, an XY precision shift stage is applied to complete the sub-pixel shift process. In addition, image acquisition and high-resolution image composition are integrated in the FPD hardware. According to the relevant standards for detector image quality evaluation, we tested and evaluated some image quality indicators. The results show that the proposed FPD with SPS outperforms the original FPD without SPS technology. More specifically, the measured pixel size of the proposed FPD was reduced from 162 to 140 μm for 2 × 2 sub-pixel shift mode, and 132 μm for 4 × 4 sub-pixel shift mode, that is, the basic spatial detector resolution was improved by 13.6% for the simplest 2 × 2 sub-pixel shift mode, and by 18.5% for 4 × 4 sub-pixel shift mode. With this method, a lower-price FPD is elevated both in resolution and  SNRn to meet imaging quality requirements. Full article
(This article belongs to the Special Issue Solid Surfaces, Defects and Detection)
Show Figures

Figure 1

19 pages, 51310 KiB  
Article
A Variable Attention Nested UNet++ Network-Based NDT X-ray Image Defect Segmentation Method
by Jiayin Liu and Jae Ho Kim
Coatings 2022, 12(5), 634; https://doi.org/10.3390/coatings12050634 - 05 May 2022
Cited by 5 | Viewed by 1669
Abstract
In this paper, we describe a new method for non-destructive testing (NDT) X-ray image defect segmentation by introducing a variable attention nested UNet++ network. To further enhance the performance of the faint defect extraction and its clear visibility, a pre-processing method based on [...] Read more.
In this paper, we describe a new method for non-destructive testing (NDT) X-ray image defect segmentation by introducing a variable attention nested UNet++ network. To further enhance the performance of the faint defect extraction and its clear visibility, a pre-processing method based on pyramid model is also added to the proposed method to effectively perform high dynamic range compression and defect enhancement on the 16-bit raw image. To illustrate its effectiveness and efficiency, we applied the proposed algorithm to the X-ray image defect segmentation problem and carried out extensive experiments. The results support that the proposed method outperforms the existing representative techniques in extracting defect for real X-ray images collected directly from industrial lines, which achieves the better performance with 89.24% IoU, and 94.31% Dice. Full article
(This article belongs to the Special Issue Solid Surfaces, Defects and Detection)
Show Figures

Figure 1

12 pages, 2117 KiB  
Article
Detection of Complex Features of Car Body-in-White under Limited Number of Samples Using Self-Supervised Learning
by Chuang Liu, Kang Su, Long Yang, Jie Li and Jingbo Guo
Coatings 2022, 12(5), 614; https://doi.org/10.3390/coatings12050614 - 29 Apr 2022
Cited by 5 | Viewed by 1118
Abstract
The measurement and monitoring of the dimensional characteristics of the body-in-white is an important part of the automobile manufacturing process. The process of using key point regression technology to perform online detection of complex features on body-in-white currently faces a bottleneck problem, namely [...] Read more.
The measurement and monitoring of the dimensional characteristics of the body-in-white is an important part of the automobile manufacturing process. The process of using key point regression technology to perform online detection of complex features on body-in-white currently faces a bottleneck problem, namely limited training samples. Under the condition that the number of labeled normal map samples is limited, this paper proposes a framework for domain-independent self-supervised learning using a large number of original images. Under this framework, a self-supervised pre-order task is designed, which uses a large number of easily accessible unlabeled original images for characterization learning as well as a domain discriminator to conduct adversarial training on the feature extractor, so that the extracted representation is domain-independent. Finally, in the key point regression task of five different complex features, a series of comparative experiments were carried out between the method in this paper and benchmark methods such as supervised learning, conventional self-supervised learning, and domain-related self-supervised learning. The results show that the method proposed in this paper has achieved significant performance advantages. In the principal component analysis of extracting features, the representation extracted by the method in this paper does not show obvious domain information. Full article
(This article belongs to the Special Issue Solid Surfaces, Defects and Detection)
Show Figures

Figure 1

Review

Jump to: Research

30 pages, 2701 KiB  
Review
Steel Surface Defect Recognition: A Survey
by Xin Wen, Jvran Shan, Yu He and Kechen Song
Coatings 2023, 13(1), 17; https://doi.org/10.3390/coatings13010017 - 22 Dec 2022
Cited by 31 | Viewed by 4525
Abstract
Steel surface defect recognition is an important part of industrial product surface defect detection, which has attracted more and more attention in recent years. In the development of steel surface defect recognition technology, there has been a development process from manual detection to [...] Read more.
Steel surface defect recognition is an important part of industrial product surface defect detection, which has attracted more and more attention in recent years. In the development of steel surface defect recognition technology, there has been a development process from manual detection to automatic detection based on the traditional machine learning algorithm, and subsequently to automatic detection based on the deep learning algorithm. In this paper, we discuss the key hardware of steel surface defect detection systems and offer suggestions for related options; second, we present a literature review of the algorithms related to steel surface defect recognition, which includes traditional machine learning algorithms based on texture features and shape features as well as supervised, unsupervised, and weakly supervised deep learning algorithms (Incomplete supervision, inexact supervision, imprecise supervision). In addition, some common datasets and algorithm performance evaluation metrics in the field of steel surface defect recognition are summarized. Finally, we discuss the challenges of the current steel surface defect recognition algorithms and the corresponding solutions, and our future work focus is explained. Full article
(This article belongs to the Special Issue Solid Surfaces, Defects and Detection)
Show Figures

Figure 1

Back to TopTop