Anomaly detection in formed sheet metals using convolutional autoencoders

Heger, Jens; Desai, Gururaj; Abdine, Mazhar Zein El

doi:10.1016/j.procir.2020.04.106

Cited by 9 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers from the Technical University of Sofia, Bulgaria, have successfully used an autoencoder to test print quality compared with traditional methods [ 38 ]. Other examples of the use of autoencoders relate to testing the quality of electrode coating in the automotive industry [ 39 ], testing the quality of sheet metal using data obtained directly from production [ 40 ], controlling the printed circuit board using data from production [ 41 ] and on artificial data [ 42 ]. In addition, there are numerous other examples of using autoencoders to test quality in production tasks [ 43 , 44 , 45 ].…”

Section: Related Workmentioning

confidence: 99%

Ultra-Lightweight Fast Anomaly Detectors for Industrial Applications

Kocon,

Malesa,

Rapcewicz

2023

Sensors

View full text Add to dashboard Cite

Quality inspection in the pharmaceutical and food industry is crucial to ensure that products are safe for the customers. Among the properties that are controlled in the production process are chemical composition, the content of the active substances, and visual appearance. Although the latter may not influence the product’s properties, it lowers customers’ confidence in drugs or food and affects brand perception. The visual appearance of the consumer goods is typically inspected during the packaging process using machine vision quality inspection systems. In line with the current trends, the processing of the images is often supported with deep neural networks, which increases the accuracy of detection and classification of faults. Solutions based on AI are best suited to production lines with a limited number of formats or highly repeatable production. In the case where formats differ significantly from each other and are often being changed, a quality inspection system has to enable fast training. In this paper, we present a fast method for image anomaly detection that is used in high-speed production lines. The proposed method meets these requirements: It is easy and fast to train, even on devices with limited computing power. The inference time for each production sample is sufficient for real-time scenarios. Additionally, the ultra-lightweight algorithm can be easily adapted to different products and different market segments. In this work, we present the results of our algorithm on three different real production data gathered from food and pharmaceutical industries.

show abstract

Section: Related Workmentioning

confidence: 99%

Ultra-Lightweight Fast Anomaly Detectors for Industrial Applications

Kocon,

Malesa,

Rapcewicz

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Autoencoder is also well-known as a dimensionality reduction algorithm, feature detector, generative model, or unsupervised pretraining of deep learning model. Several implementations of this neural network in computer vision area are image denoising [20], augmentation data [20], anomaly detection [21,22], image restoration [23] and invertible grayscale [24]. In another case, the execution of autoencoder in a two-level segmentation task or binarization task still needs labeled image or ground truth binary image.…”

Section: Convolutional Autoencoder Networkmentioning

confidence: 99%

“…During the model training process, each decoder block uses transposed convolution with the same stride as the encoder to up sample the input and learn how to fill in missing parts. In addition, some researchers demonstrated the use of a pooling layer for down sampling in the encoder and an up-sampling method in the decoder, as explained by [22], allows to solve the problem of anomaly image detection. In the case of image restoration using the Residual Encoder-Decoder Network (RED-Net), a pooling layer is not recommended for down sampling because deconvolution in the decoder does not work well [23].…”

Section: Convolutional Autoencoder Networkmentioning

confidence: 99%

Binarization Strategy Using Multiple Convolutional Autoencoder Network for Old Sundanese Manuscript Images

Paulus

Burie

Verbeek

2021

Document Analysis and Recognition – ICDAR 2021 Workshops

View full text Add to dashboard Cite

The binarization step for old documents is still a challenging task even though many hand-engineered and deep learning algorithms have been offered. In this research work, we address foreground and background segmentation using a convolutional autoencoder network with 3 supporting components. The assessment of several hyper-parameters including the window size, the number of convolution layers, the kernel size, the number of filters as well as the number of encoder-decoder layers on the network is conducted. In addition, the skip connections approach is considered in the decoding procedure. Moreover, we evaluated the summation and concatenation function before the up-sampling process to reuse the previous low-level feature maps and to enrich the decoded representation. Based on several experiments, we determined that kernel size, the number of filters, and the number of encoder-decoder blocks have a little impact in term of binarization performance. While the window size and multiple convolutional layers are more impactful than other hyper-parameters. However, they require more storage and may increase computation costs. Moreover, a careful embedding of batch normalization and dropout layers also provides a contribution to handle overfitting in the deep learning model. Overall, the multiple convolutional autoencoder network with skip connection successfully enhances the binarization accuracy on old Sundanese palm leaf manuscripts compared to preceding state of the art methods.

show abstract