Automatic detection of welding defects using the convolutional neural network

Sizyakin, Roman; Voronin, Viacheslav; Gapon, Nikolay; Zelensky, Alexander A.; Pižurica, Aleksandra

doi:10.1117/12.2525643

Cited by 27 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the analysis of the results obtained (see Figure 3 and Table 1), several conclusions can be drawn. Morphological filtering is an effective auxiliary technique in cases of necessity: pre-localization of cracks, 26,27 creation of virtual modalities, 28 or post-processing, which was demonstrated in this paper. As an independent method for detecting cracks, morphological filtering in most cases will have poor accuracy.…”

Section: Resultsmentioning

confidence: 89%

A deep learning approach to crack detection on road surfaces

Sizyakin

Voronin

Gapon

et al. 2020

Artificial Intelligence and Machine Learning in Defense Applications II

Self Cite

View full text Add to dashboard Cite

Currently, modern achievements in the field of deep learning are increasingly being applied in practice. One of the practical uses of deep learning is to detect cracks on the surface of the roadway. The destruction of the roadway is the result of various factors: for example, the use of low-quality material, non-compliance with the standards of laying asphalt, external physical impact, etc. Detection of these damages in automatic mode with high speed and accuracy is an important and complex task. An effective solution to this problem can reduce the time of services that carry out the detection of damage and also increase the safety of road users. The main challenge for automatically detecting such damage, in most cases, is the complex structure of the roadway. To accurately detect this damage, we use U-Net. After that we improve the binary map with localized cracks from the U-Net neural network, using the morphological filtering. This solution allows localizing cracks with higher accuracy in comparison with traditional methods crack detection, as well as modern methods of deep learning. All experiments were performed using the publicly available CRACK500 dataset with examples of cracks and their binary maps.

show abstract

Section: Resultsmentioning

confidence: 89%

A deep learning approach to crack detection on road surfaces

Sizyakin

Voronin

Gapon

et al. 2020

Artificial Intelligence and Machine Learning in Defense Applications II

Self Cite

View full text Add to dashboard Cite

show abstract

“…Two different deep convolutional neural networks [30] are trained on the same image set, and then they are transformed into a multi-model integrated frameworks to reduce the error rate. Sizyakin et al [31] integrated convolutional neural network and support vector machine, which improves positioning accuracy. A simplified YOLO v3 network is designed in [8] through optimizing the loss function, and it obtains a great detection results.…”

Section: Weld Defect Detectionmentioning

confidence: 99%

LF-YOLO: A Lighter and Faster YOLO for Weld Defect Detection of X-ray Image

Liu¹,

Chen²,

He³

et al. 2021

Preprint

View full text Add to dashboard Cite

X-ray image plays an important role in manufacturing for quality assurance, because it can reflect the internal condition of weld region. However, the shape and scale of different defect types vary greatly, which makes it challenging for model to detect weld defects. In this paper, we propose a weld defect detection method based on convolution neural network (CNN), namely Lighter and Faster YOLO (LF-YOLO). In particularly, an enhanced multiscale feature (EMF) module is designed to implement both parameter-based and parameter-free multi-scale information extracting operation. EMF enables the extracted feature map capable to represent more plentiful information, which is achieved by superior hierarchical fusion structure. To improve the performance of detection network, we propose an efficient feature extraction (EFE) module. EFE processes input data with extremely low consumption, and improve the practicability of whole network in actual industry. Experimental results show that our weld defect network achieves satisfactory balance between performance and consumption, and reaches 92.9 mAP50 with 61.5 FPS. To further prove the ability of our method, we test it on public dataset MS COCO, and the results show that our LF-YOLO has a outstanding versatility detection performance.

show abstract

“…However, some actual cracks may be lost as well. In the literature, multiscale convolutional networks [44]- [47] are often used to solve this problem. However, the computational complexity of these models is still prohibitive for processing very high-resolution data in multiple modalities as we need to do, especially when user interaction and re-training processes are a requirement.…”

Section: Enhancing the Accuracy Of The Crack Localizationmentioning

confidence: 99%

Crack Detection in Paintings Using Convolutional Neural Networks

et al. 2020

Self Cite

View full text Add to dashboard Cite

The accurate detection of cracks in paintings, which generally portray rich and varying content, is a challenging task. Traditional crack detection methods are often lacking on recent acquisitions of paintings as they are poorly adapted to high-resolutions and do not make use of the other imaging modalities often at hand. Furthermore, many paintings portray a complex or cluttered composition, significantly complicating a precise detection of cracks when using only photographic material. In this paper, we propose a fast crack detection algorithm based on deep convolutional neural networks (CNN) that is capable of combining several imaging modalities, such as regular photographs, infrared photography and X-Ray images. Moreover, we propose an efficient solution to improve the CNN-based localization of the actual crack boundaries and extend the CNN architecture such that areas where it makes little sense to run expensive learning models are ignored. This allows us to process large resolution scans of paintings more efficiently. The proposed on-line method is capable of continuously learning from newly acquired visual data, thus further improving classification results as more data becomes available. A case study on multimodal acquisitions of the Ghent Altarpiece, taken during the currently ongoing conservation-restoration treatment, shows improvements over the state-of-the-art in crack detection methods and demonstrates the potential of our proposed method in assisting art conservators.INDEX TERMS Digital painting analysis, crack detection, virtual restoration, machine learning, morphological filtering, convolutional neural networks, transfer learning, multimodal data, Ghent Altarpiece.

show abstract

Automatic detection of welding defects using the convolutional neural network

Cited by 27 publications

References 18 publications

A deep learning approach to crack detection on road surfaces

A deep learning approach to crack detection on road surfaces

LF-YOLO: A Lighter and Faster YOLO for Weld Defect Detection of X-ray Image

Crack Detection in Paintings Using Convolutional Neural Networks

Contact Info

Product

Resources

About