Adaptive Vision Based Condition Monitoring and Fault Detection Method for Multi Robots at Production Lines in Industrial Systems

Yetiş, Hasan; Karaköse, Mehmet

doi:10.18100/ijamec.270410

Cited by 13 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…VAE utilizes this trick to realize random sampling from multivariate Gaussian distributions. As shown in (2), as shown at the bottom of this page, it learns to generate data which maximizes a variational lower bound of the model log-likelihood…”

Section: A Conditional Variational Auto-encodermentioning

confidence: 99%

“…In many practical applications, such as vision-based industrial fault monitoring [1], [2] and medical image based disease diagnosis [3]- [5], people would like to detect the anomalies that don't belong to any of the known classes so as to determine if the situation is within normal. In these cases, pictures of normal categories are available.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel and Efficient CVAE-GAN-Based Approach With Informative Manifold for Semi-Supervised Anomaly Detection

et al. 2019

View full text Add to dashboard Cite

Semi-supervised anomaly detection identifies abnormal (testing) observations which are different from normal (training) observations. In many practical situations, anomalies are poorly insufficient and not well defined, while the normal data are easily sampled, have a wide variety, and may not be classified. For this paradigm, we propose a novel end-to-end deep network as an anomaly detector only trained on normal samples. Our architecture consists of a conditional variational auto-encoder (CVAE), a feature discriminator (FD), and an adversarially trained WGAN-GP discriminator. The CVAE is designed as a generator to reconstruct images. It leverages underlying category information and multivariate Gaussian distributions to regularize the latent space, enabling a smooth and informative manifold. For anomalies which have a certain similarity to normal data, we perform active negative training by generating potential outliers from the latent space to limit network generative capability. In order to capture data characteristics, we maximize the mutual information between the inputs and the latent codes by the FD. It enhances the relationship between the high-dimensional image space and corresponding encoded vectors. To promote reconstruction, a structural similarity loss is applied to robustly recover local texture details and the WGAN-GP discriminator is employed to aid in generating photo-realistic images. We distinguish anomalies by computing a reconstruction-based anomaly score. Different from recent encoder-decoder or GAN-based architectures, our approach considers input categories, constructs, and exploits a useful manifold in an unsupervised manner and has a stronger reconstruction capability. The experimental results demonstrate that the proposed approach outperforms state-of-the-art methods over several benchmark datasets. INDEX TERMS Semi-supervised anomaly detection, conditional variational auto-encoder, generative adversarial networks, informative manifold, structural similarity loss.

show abstract

Section: A Conditional Variational Auto-encodermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Novel and Efficient CVAE-GAN-Based Approach With Informative Manifold for Semi-Supervised Anomaly Detection

et al. 2019

View full text Add to dashboard Cite

show abstract

“…BirleĢtirilecek görüntülerin sayısından bağımsız olarak, görüntü mozaikleme iĢlemi her adımda sadece iki resim arasında gerçekleĢir [17]. Resimlerden bir tanesi referans, diğeri ise hedef görüntü olarak adlandırılır.…”

Section: Görüntü Mozai̇kleme (Image Mosaicing)unclassified

Optimizasyon Tabanlı Adaptif Görüntü Mozaikleme Algoritması

Karaköse

Yetiş

Müezzinoğlu

2017

Bilişim Teknolojileri Dergisi

Self Cite

View full text Add to dashboard Cite

Özet-Görüntü iĢleme, dijital ortamdaki görüntüler üzerinde bir amaç doğrultusunda gerekli analizler veya değiĢikliklerin yapılmasına yönelik çalıĢmaları kapsamaktadır. Son zamanlarda görüntü iĢleme tekniklerinden en çok kullanılanlardan biri de ortak sahneleri içeren resimler üzerinde iĢlem yapan ve bunları çakıĢtırarak birleĢtiren görüntü mozaikleme iĢlemidir. Bu çalıĢmada kendi kameramızdan elde ettiğimiz görüntüler üzerinde MATLAB ortamında görüntü mozaikleme iĢlemi gerçekleĢtirilmiĢtir. Görüntü mozaikleme için, özellik tabanlı görüntü mozaiklemenin temel adımları olan anahtar noktaların tespiti, bu noktaların eĢleĢtirilmesi, hatalı eĢleĢmelerin elenmesi ve homografi tahmini uygulanmıĢtır. Uygulamada özellik çıkarımı için SIFT algoritması seçilmiĢ, elde edilen homografi matrisi yardımı ile gerekli dönüĢüm iĢlemleri uygulanarak görüntü mozaikleme iĢlemi gerçekleĢtirilmiĢtir. Mozaikleme iĢleminin kalitesini artırmak adına optimizasyon yöntemi olan genetik algoritmadan yararlanılmıĢtır. Uygulamada giriĢ görüntü sayıları ve mozaikleme parametreleri farklı seçilerek çeĢitli karĢılaĢtırma iĢlemleri yapılmıĢtır.Anahtar Kelimeler-Genetik algoritma, Görüntü iĢleme, Görüntü mozaikleme, Optimizasyon. Optimization Based Adaptive Image Mosaicing AlgorithmAbstract-Image processing involves studies to make necessary analyzes or changes in an image aimed at digital images. One of the most recent use of image processing techniques is image mosaicking, which processes and combines images containing common scenes. In this study, we performed image mosaicing in the MATLAB environment on the images we acquired from our own camera. The key steps for feature-based image mosaicking which are detection of key points, matching of these points, elimination of mismatches and homography estimation are applied for image mosaicing. In the application, the SIFT algorithm was selected for feature extraction and image transformation was performed with the help of the obtained homography matrix. In order to increase the quality of the mosaic process, genetic algorithm, which is an optimization method, has been used. Various comparisons were performed by taking different input counts and by choosing different image mosaicing parameters.

show abstract

“…As monitors get smaller and smaller, such as those used in ultra-thin panels and smart wearable devices, the likelihood of Mura defects in the manufacturing process will only increase, so achieving automatic detection of Mura makes sense. Anomaly detection is common in various fields [1][2][3][4][5][6]. In [7,8], Young-Jin Cha et al successfully applied deep learning to defect detection and achieved good detection results.…”

Section: Introductionmentioning

confidence: 99%

A Mura Detection Model Based on Unsupervised Adversarial Learning

Song

Yang

Wang³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Mura is a phenomenon in which the displays have various uneven display defects and has the characteristics of irregular shape and different sizes. For Mura detection, traditional detection methods have the following two problems: One is the problem of data imbalance. The second is that new shapes and sizes of Mura may appear at any time during the inspection process. In response to the above problems, this paper proposes the Res-unetGAN network, which is an unsupervised anomaly detection method based on generative adversarial network. The generative network is an autoencoder structure composed of ResNet50 and UNet to learn the normal distribution of normal samples. The discriminator is a convolutional neural network based on deep separable convolution and forms a game process with the generator. The network only needs normal samples during the training process, and the network is optimized by the error loss between the original samples and the reconstructed samples. In the test, a reconstruction error score will be designed according to the reconstruction quality, and the defect in the sample will be judged by the reconstruction error score, so as to achieve the goal of anomaly detection. After repeated experiments on the Mura data set, the detection accuracy of Mura defect is better than that of several models compared. The proposed model has a unique application prospect in other industrial anomaly detection since it only requires normal samples for training.

show abstract

Adaptive Vision Based Condition Monitoring and Fault Detection Method for Multi Robots at Production Lines in Industrial Systems

Cited by 13 publications

References 18 publications

A Novel and Efficient CVAE-GAN-Based Approach With Informative Manifold for Semi-Supervised Anomaly Detection

A Novel and Efficient CVAE-GAN-Based Approach With Informative Manifold for Semi-Supervised Anomaly Detection

Optimizasyon Tabanlı Adaptif Görüntü Mozaikleme Algoritması

A Mura Detection Model Based on Unsupervised Adversarial Learning

Contact Info

Product

Resources

About