相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Review
Materials Science, Multidisciplinary
Xin Wen et al.
Summary: Steel surface defect recognition is important in industrial defect detection and has gained increasing attention. This paper discusses the key hardware and options for steel surface defect detection systems, and provides a literature review of algorithms for steel surface defect recognition, including traditional machine learning algorithms based on texture and shape features, as well as supervised, unsupervised, and weakly supervised deep learning algorithms. Common datasets and algorithm performance evaluation metrics in this field are also summarized. Lastly, the challenges and corresponding solutions for current steel surface defect recognition algorithms are discussed, along with the future work focus.
Review
Computer Science, Artificial Intelligence
Alireza Saberironaghi et al.
Summary: In recent decades, detecting surface defects has become a challenging task. Traditional image processing techniques struggle with complex textures, noise, and lighting differences. Deep learning has emerged as a solution due to accessibility to computing power and the rapid digitization of society. This review paper summarizes and analyzes the current state of research on defect detection using machine learning methods, discussing detection on industrial products from supervised, semi-supervised, and unsupervised perspectives, as well as the research status of defect detection methods for X-ray images. Common challenges and potential solutions in surface defect detection are also highlighted.
Article
Engineering, Electrical & Electronic
Hu Feng et al.
Summary: This article proposes a simple and effective few-shot segmentation method called CPANet, which aims to learn a network that can segment untrained S3D categories with only a few labeled defective samples. CPANet effectively aggregates long-range relationships of discrete defects using CPP and SA modules. It also introduces an SSA module to aggregate multiscale context information of defect features and suppresses interference from background information. Extensive experiments demonstrate that CPANet achieves state-of-the-art performance on the FSSD-12 dataset.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Engineering, Multidisciplinary
Yanfen Li et al.
Summary: This paper introduces an automatic instance segmentation-based defect analysis framework, which addresses the issues of blurriness and vaporous environment in traditional sewer defect inspection approaches. It presents a novel defect segmentation model and a publicly available dataset. Experimental results demonstrate a significant improvement in mean Average Precision.
Article
Materials Science, Multidisciplinary
Chi Wan et al.
Summary: The detection of no-service rail surface defects is crucial in the rail manufacturing process to prevent financial losses. However, these defects are often difficult to distinguish from the background, posing a challenge for accurate identification. In this study, we introduce salient object detection through machine vision and propose an innovative deep learning network called Two-Stream Swin Transformer Network (TSSTNet) for detecting these defects on rail surfaces.
Article
Materials Science, Multidisciplinary
Yu He et al.
Summary: This study proposes a semi-supervised framework based on deep learning techniques for texture surface defect classification, utilizing generative adversarial networks and convolutional neural networks. A novel label assignment scheme is introduced to integrate unlabeled samples into semi-supervised learning for enhanced system performance.
Proceedings Paper
Computer Science, Artificial Intelligence
Karsten Roth et al.
Summary: This paper addresses the critical issue of identifying defective parts in large-scale industrial manufacturing. The authors propose a solution that fits a model using nominal example images and combines embeddings from ImageNet models with an outlier detection model. The proposed approach achieves state-of-the-art performance while offering competitive inference times.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Chaoqin Huang et al.
Summary: This paper proposes a few-shot anomaly detection method that trains a category-agnostic model using a registration task and outperforms existing methods in experiments.
COMPUTER VISION, ECCV 2022, PT XXIV
(2022)
Article
Engineering, Multidisciplinary
Yanyan Wang et al.
Summary: This article proposes a new method called RENet for accurate and robust pavement crack detection, utilizing a rectangular convolution pyramid and edge enhancement network. Experimental results demonstrate that this method surpasses other state-of-the-art algorithms in terms of robustness and universality.
Article
Computer Science, Interdisciplinary Applications
Yucheng Wang et al.
Summary: This paper proposes a new graph-based semi-supervised method, MMGCN, for surface defect classification, which outperforms other semi-supervised methods in terms of both performance and class separation.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2021)
Article
Multidisciplinary Sciences
Xinglong Feng et al.
Summary: This study proposed a new hot rolled steel strip defect dataset X-SDD for the actual detection of defects on the surface of hot rolled steel strip. Various algorithms were tested on X-SDD, with the results showing that the proposed algorithm achieved high accuracy and outperformed other comparable algorithms.
Article
Engineering, Multidisciplinary
Yingying Xu et al.
Summary: This paper proposes a novel tunnel defect inspection method based on Mask R-CNN, with detailed studies on PAFPN and the edge detection branch, showing their robustness and accuracy in tunnel defect detection and segmentation.
Article
Engineering, Multidisciplinary
Yu Feng Shu et al.
Summary: This paper proposes a method for detecting and identifying commutator surface defects, by applying YOLOv3 target detection to commutator surface defect detection and recognition, designing a network with smaller model size, fewer parameters, and faster running time, and achieving good accuracy in experiments.
Proceedings Paper
Computer Science, Artificial Intelligence
Shelly Sheynin et al.
Summary: The study introduces a hierarchical generative model for few-shot anomaly detection in images, capturing multi-scale patch distribution of training images. By using image transformations and optimizing scale-specific patch-discriminators, the model representation is enhanced, showing superior performance compared to recent baseline methods.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Article
Automation & Control Systems
Jianzhu Wang et al.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2020)
Article
Chemistry, Analytical
Xiaoming Lv et al.
Article
Multidisciplinary Sciences
Jieun Park et al.
Article
Engineering, Multidisciplinary
Jie Gao et al.
Article
Engineering, Electrical & Electronic
Poojan Oza et al.
IEEE SIGNAL PROCESSING LETTERS
(2019)
Proceedings Paper
Computer Science, Information Systems
Guansong Pang et al.
KDD'19: PROCEEDINGS OF THE 25TH ACM SIGKDD INTERNATIONAL CONFERENCCE ON KNOWLEDGE DISCOVERY AND DATA MINING
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Pramuditha Perera et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Article
Engineering, Electrical & Electronic
Antonia Creswell et al.
IEEE SIGNAL PROCESSING MAGAZINE
(2018)
Article
Computer Science, Artificial Intelligence
Jing Yang et al.
Proceedings Paper
Computer Science, Information Systems
Thomas Schlegl et al.
INFORMATION PROCESSING IN MEDICAL IMAGING (IPMI 2017)
(2017)
Article
Chemistry, Physical
Kechen Song et al.
APPLIED SURFACE SCIENCE
(2013)
Article
Computer Science, Software Engineering
S Dasgupta et al.
RANDOM STRUCTURES & ALGORITHMS
(2003)