Fully automatic detection of anomalies on wheels surface using an adaptive accurate model and hypothesis testing theory

Tout, Karim; Cogranne, Rémi; Retraint, Florent

doi:10.1109/eusipco.2016.7760300

Cited by 5 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If a feature vector lies outside the hypersphere found by SVDD during testing, the image patch corresponding to this feature vector is considered anomalous. Similar works can be found in [18][19][20]. Compared to these traditional dimensionality reduction models, a convolutional neural network (CNN) provides nonlinear mapping and is better at extracting semantic information.…”

Section: Feature Extraction Based Methodsmentioning

confidence: 81%

Image Anomaly Detection Using Normal Data Only by Latent Space Resampling

et al. 2020

View full text Add to dashboard Cite

Detecting image anomalies automatically in industrial scenarios can improve economic efficiency, but the scarcity of anomalous samples increases the challenge of the task. Recently, autoencoder has been widely used in image anomaly detection without using anomalous images during training. However, it is hard to determine the proper dimensionality of the latent space, and it often leads to unwanted reconstructions of the anomalous parts. To solve this problem, we propose a novel method based on the autoencoder. In this method, the latent space of the autoencoder is estimated using a discrete probability model. With the estimated probability model, the anomalous components in the latent space can be well excluded and undesirable reconstruction of the anomalous parts can be avoided. Specifically, we first adopt VQ-VAE as the reconstruction model to get a discrete latent space of normal samples. Then, PixelSail, a deep autoregressive model, is used to estimate the probability model of the discrete latent space. In the detection stage, the autoregressive model will determine the parts that deviate from the normal distribution in the input latent space. Then, the deviation code will be resampled from the normal distribution and decoded to yield a restored image, which is closest to the anomaly input. The anomaly is then detected by comparing the difference between the restored image and the anomaly image. Our proposed method is evaluated on the high-resolution industrial inspection image datasets MVTec AD which consist of 15 categories. The results show that the AUROC of the model improves by 15% over autoencoder and also yields competitive performance compared with state-of-the-art methods.

show abstract

Section: Feature Extraction Based Methodsmentioning

confidence: 81%

Image Anomaly Detection Using Normal Data Only by Latent Space Resampling

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Meanwhile the old idea of performing a background subtraction remains quite valid. Indeed, as pointed out still very recently in [137], background subtraction may be used to return to an elementary background model for the residual that might contain only noise.…”

Section: Discussionmentioning

confidence: 99%

“…We need a unified anomaly detection criterion, and we shall see that the a-contrario framework, introduced in Section 3.1, gives one. [38,60,80,105,126,137,141,142] Locally Homogeneous [25,48,51,57,63,67,68,85,88,117,120] Sparsity based [1,9,19,20,31,45,77,78,89,152] Non-local self-similar NL-means inspired [10,33,102,125,132,153] Kernel PCA [62] Diffusion maps [8,29,53,84,95,96,106] 3 Estimating a number of false alarms for all compared methods…”

Section: Conclusion Selection Of the Methods And Their Synthesismentioning

confidence: 99%

“…A very recent and exemplary method to detect anomalies in smooth materials is the one proposed by Tout et al [137]. In this paper, the authors develop a method for the fully automatic detection of anomalies on wheels surface.…”

Section: Homogeneous Background Modelmentioning

confidence: 99%

“…They avoid proposing a stochastic model for an often complex background by computing the distance to the background or doing background subtraction. However this simplification comes at a cost: some algorithms are hard to generalize to new applications, and the detection decision mechanism is generally not statistically justified, with the exception of some methods, like Tout et al [137].…”

Section: Homogeneous Background Modelmentioning

confidence: 99%

See 2 more Smart Citations

Image Anomalies: A Review and Synthesis of Detection Methods

et al. 2019

View full text Add to dashboard Cite

We review the broad variety of methods that have been proposed for anomaly detection in images. Most methods found in the literature have in mind a particular application. Yet we focus on a classification of the methods based on the structural assumption they make on the "normal" image, assumed to obey a "background model". Five different structural assumptions emerge for the background model. Our analysis leads us to reformulate the best representative algorithms in each class by attaching to them an a-contrario detection that controls the number of false positives and thus deriving a uniform detection scheme for all. By combining the most general structural assumptions expressing the background's normality with the proposed generic statistical detection tool, we end up proposing several generic algorithms that seem to generalize or reconcile most methods. We compare the six best representatives of our proposed classes of algorithms on anomalous images taken from classic papers on the subject, and on a synthetic database. Our conclusion hints that it is Both authors contributed equally to this work. possible to perform automatic anomaly detection on a single image.

show abstract