1,740 Hits in 4.4 sec

Synthetic Defect Generation for Display Front-of-Screen Quality Inspection: A Survey [article]

Shancong Mou, Meng Cao, Zhendong Hong, Ping Huang, Jiulong Shan, Jianjun Shi
2022 arXiv   pre-print
Synthetic defect data generation can help address this issue.  ...  However, the severe imbalanced data, especially the limited number of defect samples, has been a long-standing problem that hinders the successful application of deep learning algorithms.  ...  Even though there are considerable advancements in unsupervised/semi-supervised learning approaches in anomaly/defect detection, supervised learning-based defect detection techniques are more popular due  ... 
arXiv:2203.03429v1 fatcat:ozjhpcusv5gotle55xscrsj3m4

Human-Centric Artificial Intelligence Architecture for Industry 5.0 Applications [article]

Jože M. Rožanec, Inna Novalija, Patrik Zajec, Klemen Kenda, Hooman Tavakoli, Sungho Suh, Entso Veliou, Dimitrios Papamartzivanos, Thanassis Giannetsos, Sofia Anna Menesidou, Ruben Alonso, Nino Cauli (+8 others)
2022 arXiv   pre-print
Therefore, we propose an architecture that integrates Artificial Intelligence (Active Learning, Forecasting, Explainable Artificial Intelligence), simulated reality, decision-making, and users' feedback  ...  , focusing on synergies between humans and machines.  ...  In supervised machine learning models, this is realized by selecting unlabeled data, which can lead to the best models' learning outcomes, and request labels to a human annotator.  ... 
arXiv:2203.10794v1 fatcat:xt2gbrdi5vekbchzisrhq5yx2q

Synthetic Data Generation for Steel Defect Detection and Classification Using Deep Learning

Aleksei Boikov, Vladimir Payor, Roman Savelev, Alexandr Kolesnikov
2021 Symmetry  
In both cases, the neural networks showed good results in the classification and segmentation of surface defects of steel workpieces in the image.  ...  Dice score on synthetic data reaches 0.62, and accuracy—0.81.  ...  Currently, machine learning methods applied as part of steel slab surface inspection systems require a large number of defect images for training.  ... 
doi:10.3390/sym13071176 fatcat:msdoxj4ypzg3jbua647sk6x2gm

A sight on defect detection methods for imbalanced industrial data

Meryem Chaabi, Mohamed Hamlich, S. Krit
2022 ITM Web of Conferences  
Which make it quite difficult to apply supervised algorithms as their performances decrease by training the model on imbalanced data.  ...  Product defect detection is a challenging task, especially in situations where is difficult and costly to collect defect samples.  ...  [11] developed a generic semi-supervised deep learning model for automated surface inspection using data augmentation.  ... 
doi:10.1051/itmconf/20224301012 fatcat:s4gqwaepf5hvtirz5gvijzf5rq

A Generic Semi-supervised Deep Learning-Based Approach for Automated Surface Inspection

Xiaoqing Zheng, Hongcheng Wang, Jie Chen, Yaguang Kong, Song Zheng
2020 IEEE Access  
INDEX TERMS Automated surface inspection, defect detection, deep learning, machine vision, MixMatch, semi-supervised learning.  ...  of surfaces and defects.  ...  Learning-based methods train a system to classify defects by using pattern recognition algorithms such as support vector machines (SVMs) [13] , artificial neural networks (ANNs) [14] , and k-nearest  ... 
doi:10.1109/access.2020.3003588 fatcat:wm3gcgqaq5dgzpaeebtiiysmwi

Microwave Nondestructive Testing for Defect Detection in Composites Based on K-means Clustering Algorithm

Nawaf H. M. M. Shrifan, Ghassan N. Jawad, Nor Ashidi Mat Isa, Muhammad Firdaus Akbar
2020 IEEE Access  
At present, the defect evaluation using an unsupervised machine learning-based microwave NDT technique is not reported elsewhere.  ...  In this research, a novel microwave NDT technique is presented based on k-means unsupervised machine learning for defect detection in composites.  ...  Furthermore, supervised machine learning such as ANN and SVM may provide significant results in term of the defect's size due to the learning-based process while a suitable training sample is provided.  ... 
doi:10.1109/access.2020.3048147 fatcat:ndvgjbmifje23pu7aiekbgh2sy

Anomaly Detection using Deep Learning based Image Completion [article]

Matthias Haselmann, Dieter P. Gruber, Paul Tabatabai
2018 arXiv   pre-print
Automated surface inspection is an important task in many manufacturing industries and often requires machine learning driven solutions.  ...  In this work, we instead perform one-class unsupervised learning on fault-free samples by training a deep convolutional neural network to complete images whose center regions are cut out.  ...  The PCCL is funded by the Austrian Government and the State Governments of Styria and Upper Austria.  ... 
arXiv:1811.06861v1 fatcat:oak3akf57zgrxejjnmjoj4awqi

Deep Quality Assessment of a Solar Reflector Based on Synthetic Data: Detecting Surficial Defects from Manufacturing and Use Phase

Alexios Papacharalampopoulos, Konstantinos Tzimanis, Kyriakos Sabatakakis, Panagiotis Stavropoulos
2020 Sensors  
and identify surface irregularities by classifying images as either acceptable or non-acceptable.  ...  In addition, for the full utilization of the obtained data, deep learning is now suggested for use.  ...  and non-defective solar panel reflector surfaces based on real ones.  ... 
doi:10.3390/s20195481 pmid:32987915 fatcat:mbeaaty2mnbnjf5sdrkxslcaoq

A Survey of Surface Defect Detection of Industrial Products Based on A Small Number of Labeled Data [article]

Qifan Jin
2022 arXiv   pre-print
The surface defect detection method based on visual perception has been widely used in industrial quality inspection.  ...  Deep learning-based industrial product surface defect detection methods suitable for a small number of labeled data are divided into based on data augmentation, based on transfer learning, model-based  ...  Gao [58] proposed a CNN-based semi-supervised learning method for steel surface defect recognition, and CNN was improved by Pseudo-Label (PL), an efficient semi-supervised framework that can be used  ... 
arXiv:2203.05733v1 fatcat:7imwu76dqzglvms4fivggd6r3y

Machine Learning in Production – Potentials, Challenges and Exemplary Applications

Andreas Mayr, Dominik Kißkalt, Moritz Meiners, Benjamin Lutz, Franziska Schäfer, Reinhardt Seidel, Andreas Selmaier, Jonathan Fuchs, Maximilian Metzner, Andreas Blank, Jörg Franke
2019 Procedia CIRP  
Abstract Recent trends like autonomous driving, natural language processing, service robotics or Industry 4.0 are mainly based on the tremendous progress made in the field of machine learning (ML).  ...  Abstract Recent trends like autonomous driving, natural language processing, service robotics or Industry 4.0 are mainly based on the tremendous progress made in the field of machine learning (ML).  ...  [31] describe a method for the visual inspection of machined metal parts applying a supervised learning model for the automated quality inspection of metallic surfaces based on ANN.  ... 
doi:10.1016/j.procir.2020.01.035 fatcat:7voafulfija5rddypqdd3outzq

Artificial Intelligence Assisted Infrastructure Assessment Using Mixed Reality Systems [article]

Enes Karaaslan, Ulas Bagci, F. Necati Catbas
2018 arXiv   pre-print
Such systems can potentially decrease the time and cost of infrastructure inspections by accelerating essential tasks of the inspector such as defect measurement, condition assessment and data processing  ...  This study explains in detail the described system and related methodologies of implementing attention guided semi supervised deep learning into mixed reality technology, which interacts with the human  ...  to leverage the power of existing supervised machine learning methods for damage detection (18) .  ... 
arXiv:1812.05659v1 fatcat:3x2ni3kvqrhzdctefzw3ypnxyy

Spectroscopic Ellipsometry Imaging for Process Deviation Detection via Machine Learning Approach

Thomas Alcaire, Delphine Le Cunff, Victor Gredy, Jean-Herve Tortai
2020 2020 31st Annual SEMI Advanced Semiconductor Manufacturing Conference (ASMC)  
In parallel, optical defectivity techniques are widely implemented in production lines to inspect a large number of dies and catch physical and patterning defects during the process flow.  ...  This is an innovative strategy that requires a model-less approach, combining an automatic ellipsometry mapping generation and a smart classification via a machine learning algorithm.  ...  This work has also been supported by the French ANR program Investissements d'Avenir EQUIPEX, contract number ANR-10-EQPX-33  ... 
doi:10.1109/asmc49169.2020.9185349 fatcat:orpdzlag2rburnhhf36zyjjfmy

Neural network applications in automated optical inspection: state of the arts

Hyungsuck Cho, Won Shik Park, Bahram Javidi, Demetri Psaltis
2002 Algorithms and Systems for Optical Information Processing VI  
Artificial neural networks have been proven to be an effective means to cope with the problems difficult to solve or inefficient to solve by convectional methodologies.  ...  Optical inspection techniques have been widely adopted in industrial areas since they provide fast and accurate information on product quality, process status, and machine conditions.  ...  are trained by supervised learning methods.  ... 
doi:10.1117/12.455971 fatcat:wij6lq4p5nbvfkxfmbxpo4mstm

A Review on Machine Learning Models in Injection Molding Machines

Senthil Kumaran Selvaraj, Aditya Raj, R. Rishikesh Mahadevan, Utkarsh Chadha, Velmurugan Paramasivam, Fuat Kara
2022 Advances in Materials Science and Engineering  
This review briefly explains working on machine learning and artificial neural network and optimizing injection molding in industries.  ...  Hence, there is a need for more close control over these operating parameters using various machine learning techniques.  ...  learning Supervised learning Supervised learning Supervised Supervised, unsupervised Supervised learning Algorithm used Polynomial regression techniques e artificial intelligence algorithm used is based  ... 
doi:10.1155/2022/1949061 fatcat:lzi6kpqmdzcdrbr4tagwggdtp4

Belt Tear Detection for Coal Mining Conveyors

Xiaoqiang Guo, Xinhua Liu, Hao Zhou, Rafal Stanislawski, Grzegorz Królczyk, Zhixiong Li
2022 Micromachines  
This paper provides professional guidelines and promising research directions for researchers and engineers based on the leading theories in machine vision and deep learning.  ...  Inspection and defect detection is essential for conveyor belts, both in academic research and industrial applications.  ...  In early 21st century, scholars proposed abundant machine vision-based defect detection methods with artificially designed features.  ... 
doi:10.3390/mi13030449 pmid:35334743 pmcid:PMC8955949 fatcat:6i7ongtst5b2bhudoqtzahsbfy
« Previous Showing results 1 — 15 out of 1,740 results