English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we introduce an approach for detecting modifications inassembled printed circuit boards based on photographs taken without tightcontrol over perspective and illumination conditions. One instance of thisproblem is the visual inspection of gas pumps PCBs, which can be modified byfraudsters wishing to deceive costumers or evade taxes. Given the uncontrolledenvironment and the huge number of possible modifications, we address theproblem as a case of anomaly detection, proposing an approach that is directedtowards the characteristics of that scenario, while being well-suited for othersimilar applications. The proposed approach employs a deep convolutionalautoencoder trained to reconstruct images of an unmodified board, but whichremains unable to do the same for images showing modifications. By comparingthe input image with its reconstruction, it is possible to segment anomaliesand modifications in a pixel-wise manner. Experiments performed on a datasetbuilt to represent real-world situations (and which we will make publiclyavailable) show that our approach outperforms other state-of-the-art approachesfor anomaly segmentation in the considered scenario, while producing comparableresults on the popular MVTec-AD dataset for a more general object anomalydetection task.

Image-Based Detection of Modifications in Gas Pump PCBs with Deep Convolutional Autoencoders