☆ 4.6 Article

LSA-Net: Location and shape attention network for automatic surface defect segmentation

JOURNAL OF MANUFACTURING PROCESSES (2023)

Related references

Note: Only part of the references are listed.

Review Materials Science, Multidisciplinary

Steel Surface Defect Recognition: A Survey

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.

COATINGS (2023)

Add to Collection

Article Automation & Control Systems

Attention Network for Rail Surface Defect Detection via Consistency of Intersection-over-Union(IoU)-Guided Center-Point Estimation

Xuefeng Ni et al.

Summary: In this article, a attention neural network based rail surface defect detection method is proposed, which addresses the challenges of complex background and data imbalance through techniques such as key-point estimation and cross-stage fusion. Experimental results demonstrate that the proposed method outperforms competitive methods on four surface defect datasets.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

A nondestructive automatic defect detection method with pixelwise segmentation

Lei Yang et al.

Summary: Defect detection is crucial for product quality control and repair decision-making. Nondestructive testing (NDT) is effective, but faces challenges such as complex backgrounds and class imbalance. Deep learning has improved automatic defect detection, but limitations remain due to insufficient processing of local contextual features. A novel nondestructive defect detection network, NDD-Net, incorporating an attention fusion block (AFB) and a residual dense connection convolution block (RDCCB), outperforms other related models in segmenting microdefects.

KNOWLEDGE-BASED SYSTEMS (2022)

Add to Collection

Article Chemistry, Multidisciplinary

Two-Stage Deep Learning Method for Breast Cancer Detection Using High-Resolution Mammogram Images

Bunyodbek Ibrokhimov et al.

Summary: Breast cancer screening and detection using high-resolution mammographic images is difficult in computer vision. This research proposes a new two-stage deep learning method that improves accuracy by optimizing the object detection model and tumor classification model's combination.

APPLIED SCIENCES-BASEL (2022)

Add to Collection

Article Mathematics

CASI-Net: A Novel and Effect Steel Surface Defect Classification Method Based on Coordinate Attention and Self-Interaction Mechanism

Zhong Li et al.

Summary: In this paper, a lightweight network CASI-Net based on coordinate attention and self-interaction is proposed for automatic identification of hot-rolled steel strip surface defects. Experimental results show that CASI-Net achieves accurate defect classification with reduced computation.

MATHEMATICS (2022)

Add to Collection

Article Engineering, Manufacturing

A robust digital image processing method for measuring the planar burr length at milling

Gyorgy Poka et al.

Summary: The paper aims to develop a novel algorithm for measuring the planar burr length of contours that cannot be scanned from below. The proposed method uses a digital microscope and image processing algorithms to automatically collect the height of burr along the workpiece, and it has extended measurement ability for workpieces with inner contours and no illumination from below.

JOURNAL OF MANUFACTURING PROCESSES (2022)

Add to Collection

Article Chemistry, Analytical

Two-Level Model for Detecting Substation Defects from Infrared Images

Bing Li et al.

Summary: This article presents a two-level defect detection model (TDDM) that utilizes instance segmentation and superpixel segmentation algorithms to extract target equipment and construct a temperature probability density distribution for defect recognition. The effectiveness of TDDM is verified through experiments.

SENSORS (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Randomly Attracted Rough Firefly Algorithm for histogram based fuzzy image clustering

Krishna Gopal Dhal et al.

Summary: The paper proposes a Histogram Based Fuzzy Clustering technique using an improved version of Firefly Algorithm, outperforming traditional clustering methods in terms of precision, robustness, and quality of the segmented outputs.

KNOWLEDGE-BASED SYSTEMS (2021)

Add to Collection

Article Engineering, Manufacturing

Real-time recognition of arc weld pool using image segmentation network

Rui Yu et al.

Summary: This study aims to automatically track the weld pool boundary using a U-Net deep learning network, achieving accurate detection under various welding conditions. Generating representative data through multiple welding experiments ensures the reliability and robustness of the trained network.

JOURNAL OF MANUFACTURING PROCESSES (2021)

Add to Collection

Article Engineering, Manufacturing

Defect detection of injection molding products on small datasets using transfer learning

Jiahuan Liu et al.

Summary: The paper proposes a knowledge reuse strategy to train CNN models for improved defect inspection accuracy and robustness. Experimental results show high detection accuracy with limited training samples and robustness in detecting diverse complex defects. The method is meaningful for automatic defect detection in the manufacturing process.

JOURNAL OF MANUFACTURING PROCESSES (2021)

Add to Collection

Article Automation & Control Systems

FFCNN: A Deep Neural Network for Surface Defect Detection of Magnetic Tile

Luofeng Xie et al.

Summary: An intelligent system is developed to assess the surface quality of magnetic tiles before mounting, with an end-to-end CNN architecture FFCNN proposed for automatic defect identification. FFCNN consists of three modules for feature extraction, fusion, and decision-making, with an attention mechanism introduced to focus on more representative parts. Experimental results demonstrate the effectiveness and efficiency of the developed system for magnetic tile surface defect detection.

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS (2021)

Add to Collection

Article Engineering, Manufacturing

An effective defect detection method based on improved Generative Adversarial Networks (iGAN) for machined surfaces

Qingxia Wang et al.

Summary: The article introduces an effective method based on improved Generative Adversarial Networks for defect detection on machined surfaces using positive sample training and image restoration. By constructing an improved reconstructed image network model and using the Otsu algorithm to determine the threshold of the residual image, this method is able to identify and repair defect areas.

JOURNAL OF MANUFACTURING PROCESSES (2021)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Mixed supervision for surface-defect detection: From weakly to fully supervised learning

Jakob Bozic et al.

Summary: This study proposes a deep learning architecture that relaxes the requirements of fully supervised learning methods and reduces the need for highly detailed annotations for surface-defect detection in industrial quality control. By exploring different levels of annotations and utilizing two sub-networks, the proposed method achieves state-of-the-art results on multiple datasets. Additionally, the study demonstrates that mixed supervision with a few fully annotated samples can lead to comparable performance as fully supervised models but with significantly lower annotation costs.

COMPUTERS IN INDUSTRY (2021)

Add to Collection

Review Chemistry, Multidisciplinary

Surface Defect Detection Methods for Industrial Products: A Review

Yajun Chen et al.

Summary: This paper summarizes the research status of machine learning methods in surface defect detection of industrial products, including the application of traditional machine vision and deep learning technology, key problems and solutions, as well as an overview of commonly used datasets.

APPLIED SCIENCES-BASEL (2021)

Add to Collection

Article Computer Science, Software Engineering

Surface defect saliency of magnetic tile

Yibin Huang et al.

VISUAL COMPUTER (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

A two-stage attention aware method for train bearing shed oil inspection based on convolutional neural networks

Xiao Fu et al.

NEUROCOMPUTING (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

A novel hybrid approach for crack detection

Fen Fang et al.

PATTERN RECOGNITION (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

TSASNet: Tooth segmentation on dental panoramic X-ray images by Two-Stage Attention Segmentation Network

Yue Zhao et al.

KNOWLEDGE-BASED SYSTEMS (2020)

Add to Collection

Article Automation & Control Systems

PGA-Net: Pyramid Feature Fusion and Global Context Attention Network for Automated Surface Defect Detection

Hongwen Dong et al.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2020)

Add to Collection

Article Automation & Control Systems

A Simple Guidance Template-Based Defect Detection Method for Strip Steel Surfaces

Heying Wang et al.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2019)

Add to Collection

Article Engineering, Industrial

Machine vision intelligence for product defect inspection based on deep learning and Hough transform

Jinjiang Wang et al.

JOURNAL OF MANUFACTURING SYSTEMS (2019)

Add to Collection

Article Chemistry, Multidisciplinary

An Improved MB-LBP Defect Recognition Approach for the Surface of Steel Plates

Yang Liu et al.

APPLIED SCIENCES-BASEL (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving

Jiwoong Choi et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

Add to Collection

Article Materials Science, Characterization & Testing

Accurate defect detection via sparsity reconstruction for weld radiographs

Benzhi Chen et al.

NDT & E INTERNATIONAL (2018)

Add to Collection

Article Engineering, Electrical & Electronic

Quantitative Surface Crack Evaluation Based on Eddy Current Pulsed Thermography

Xiaoqing Li et al.

IEEE SENSORS JOURNAL (2017)

Add to Collection

Article Optics

Crack detection in magnetic tile images using nonsubsampled shearlet transform and envelope gray level gradient

Chengli Yang et al.

OPTICS AND LASER TECHNOLOGY (2017)

Add to Collection

Article Engineering, Electrical & Electronic

Steel Surface Defect Detection Using a New Haar-Weibull-Variance Model in Unsupervised Manner

Kun Liu et al.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2017)

Add to Collection

Article Engineering, Electrical & Electronic

Loss Functions for Image Restoration With Neural Networks

Hang Zhao et al.

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING (2017)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Mask R-CNN

Kaiming He et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

Add to Collection

Article Engineering, Multidisciplinary

Segmentation of non-stochastic surfaces based on non-subsampled contourlet transform and mathematical morphologies

Linfu Li et al.

MEASUREMENT (2016)

Add to Collection

Article Optics

Automated defect detection in textured surfaces using optimal elliptical Gabor filters

Guang-Hua Hu

OPTIK (2015)

Add to Collection

Article Chemistry, Physical

A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects

Kechen Song et al.

APPLIED SURFACE SCIENCE (2013)

Add to Collection

Article Metallurgy & Metallurgical Engineering

Surface Detection of Continuous Casting Slabs Based on Curvelet Transform and Kernel Locality Preserving Projections

Ai Yong-hao et al.

JOURNAL OF IRON AND STEEL RESEARCH INTERNATIONAL (2013)

Add to Collection

© Peeref 2019-2024. All rights reserved.