Image Anomalies: A Review and Synthesis of Detection Methods

Ehret, Thibaud; Davy, Axel; Morel, Jean‐Michel; Delbracio, Mauricio

doi:10.1007/s10851-019-00885-0

Cited by 49 publications

(37 citation statements)

References 152 publications

(413 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The landscape of methods for unsupervised anomaly detection is diverse and many approaches have been suggested to tackle the problem (An and Cho 2015; Pereraet and Patel 219). Pimentel et al (2014) and Ehret et al (2019) give a comprehensive review of existing work. We restrict ourselves to a brief overview of current state-of-the-art methods that are able to segment anomalies, focusing on those that serve as baselines for our benchmark on the dataset.…”

Section: Methodsmentioning

confidence: 99%

The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection

et al. 2021

View full text Add to dashboard Cite

The detection of anomalous structures in natural image data is of utmost importance for numerous tasks in the field of computer vision. The development of methods for unsupervised anomaly detection requires data on which to train and evaluate new approaches and ideas. We introduce the MVTec anomaly detection dataset containing 5354 high-resolution color images of different object and texture categories. It contains normal, i.e., defect-free images intended for training and images with anomalies intended for testing. The anomalies manifest themselves in the form of over 70 different types of defects such as scratches, dents, contaminations, and various structural changes. In addition, we provide pixel-precise ground truth annotations for all anomalies. We conduct a thorough evaluation of current state-of-the-art unsupervised anomaly detection methods based on deep architectures such as convolutional autoencoders, generative adversarial networks, and feature descriptors using pretrained convolutional neural networks, as well as classical computer vision methods. We highlight the advantages and disadvantages of multiple performance metrics as well as threshold estimation techniques. This benchmark indicates that methods that leverage descriptors of pretrained networks outperform all other approaches and deep-learning-based generative models show considerable room for improvement.

show abstract

Section: Methodsmentioning

confidence: 99%

The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Note that the detection in the top right corner for both pixels and conv1 1 (and only these) seems to correspond to a defect inside the periodic pattern. More examples are available in [24].…”

Section: Methodsmentioning

confidence: 99%

“…A preliminary short version of this work was published in a conference [16]. The anomaly detection method developed here is also described briefly in our review paper [24]. Our Section 2 below summarizes some of the conclusions about the literature contained in this last paper.…”

Section: Introductionmentioning

confidence: 99%

How to Reduce Anomaly Detection in Images to Anomaly Detection in Noise

Ehret¹,

Davy²,

Delbracio³

et al. 2019

Image Processing on Line

Self Cite

View full text Add to dashboard Cite

Anomaly detectors address the difficult problem of detecting automatically exceptions in a background image, that can be as diverse as a fabric or a mammography. Detection methods have been proposed by the thousands because each problem requires a different background model. By analyzing the existing approaches, we show that the problem can be reduced to detecting anomalies in residual images (extracted from the target image) in which noise and anomalies prevail. Hence, the general and impossible background modeling problem is replaced by a simple noise model, and allows the calculation of rigorous detection thresholds. Our approach is therefore unsupervised and works on arbitrary images. The residual images can favorably be computed on dense features of neural networks. Our detector is powered by the a contrario detection theory, which avoids over-detection by fixing detection thresholds taking into account the multiple tests. Source Code The reviewed source code and documentation for this algorithm are available from the web page of this article 1. Compilation and usage instruction are included in the README.txt file of the archive.

show abstract

“…There are several methods developed for unsupervised image anomaly detection. According to Ehret et al, these unsupervised methods could be classified as nearest neighbourbased anomaly detection, clustering-based anomaly detection, statistical anomaly detection, spectral anomaly detection, and information theoretic anomaly detection [19]. In fact, if applied in a static image situation, they all belong to the first category to some extent [1], since they all measure certain distances and try to identify the discord distances of data instances.…”

Section: Related Workmentioning

confidence: 99%

“…We treat the lung CT imaging-based diagnosis of COVID-19 as a binary classification problem (e.g. COVID-19 or Non-COVID- 19). VGG and DenseNet model are applied to perform the classification.…”

Section: B Vgg and Densenetmentioning

confidence: 99%

A Two-Dimensional Sparse Matrix Profile DenseNet for COVID-19 Diagnosis Using Chest CT Images

Liu

Leung

2020

IEEE Access

View full text Add to dashboard Cite

COVID-19 is a newly identified disease, which is very contagious and has been rapidly spreading across different countries around the world, calling for rapid and accurate diagnosis tools. Chest CT imaging has been widely used in clinical practice for disease diagnosis, but image reading is still a time-consuming work. We aim to integrate an image preprocessing technology for anomaly detection with supervised deep learning for chest CT imaging-based COVID-19 diagnosis. In this study, a matrix profile technique was introduced to CT image anomaly detection in two levels. At one-dimensional level, CT images were simply flatted and transformed to a one-dimensional vector so that the matrix profile algorithm could be implemented for them directly. At two-dimensional level,a matrix profile was calculated in a sliding window way for every segment in the image. An anomaly severity score (CT-SS) was calculated, and the difference of the CT-SS between the COVID-19 CT images and Non-COVID-19 CT images was tested. A sparse anomaly mask was calculated and applied to penalize the pixel values of each image. The anomaly weighted images were then used to train standard DenseNet deep learning models to distinguish the COVID-19 CT from Non-COVID-19 CT images. A VGG19 model was used as a baseline model for comparison. Although extra finetuning needs to be done manually, the onedimensional matrix profile method could identify the anomalies successfully. Using the two-dimensional matrix profiling method, CT-SS and anomaly weighted image can be successfully generated for each image. The CT-SS significantly differed among the COVID-19 CT images and Non-COVID-19 CT images (p − value < 0.05). Furthermore, we identified a potential causal association between the number of underlying diseases of a COVID-19 patient and the severity of the disease through statistical mediation analysis. Compared to the raw images, the anomaly weighted images showed generally better performance in training the DenseNet models with different architectures for diagnosing COVID-19, which was validated using two publicly available COVID-19 lung CT image datasets. The metric Area Under the Curve(AUC) on one dataset were 0.7799(weighted)vs. 0.7391(unweighted), 0.7812(weighted) vs. 0.7410(unweighted), 0.7780(weighted) vs. 0.7399(unweighted), 0.7045(weighted) vs. 0.6910(unweighted) for DenseNet121, DenseNet169, DenseNet201, and the baseline model VGG19, respectively. The same trend was observed using another independent dataset. The significant results revealed the critical value of using this existing state-of-the-art algorithm for image anomaly detection. Furthermore, the end-to-end model structure has the potential to work as a rapid tool for clinical imaging-based diagnosis. INDEX TERMS Rare pattern mining, matrix profile, COVID-19 CT images, risk score, DenseNet, mediation analysis I. INTRODUCTION U NSUPERVISED anomaly detection using rare pattern mining is one of the most intuitive medical imaging based disease diagnosis methods [1]. People without medical expe...

show abstract

Image Anomalies: A Review and Synthesis of Detection Methods

Cited by 49 publications

References 152 publications

The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection

The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection

How to Reduce Anomaly Detection in Images to Anomaly Detection in Noise

A Two-Dimensional Sparse Matrix Profile DenseNet for COVID-19 Diagnosis Using Chest CT Images

Contact Info

Product

Resources

About