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

TL;DR

This paper presents a deep autoencoder-based method for detecting modifications in gas pump PCBs from photographs taken under uncontrolled conditions, effectively identifying anomalies and outperforms existing methods.

Contribution

It introduces a novel anomaly detection approach using deep convolutional autoencoders tailored for real-world PCB modification detection in uncontrolled environments.

Findings

Outperforms state-of-the-art anomaly segmentation methods in the specific scenario

Achieves comparable results on the MVTec-AD dataset for general anomaly detection

Provides a publicly available dataset for real-world PCB modification detection

Abstract

In this paper, we introduce an approach for detecting modifications in assembled printed circuit boards based on photographs taken without tight control over perspective and illumination conditions. One instance of this problem is the visual inspection of gas pumps PCBs, which can be modified by fraudsters wishing to deceive costumers or evade taxes. Given the uncontrolled environment and the huge number of possible modifications, we address the problem as a case of anomaly detection, proposing an approach that is directed towards the characteristics of that scenario, while being well-suited for other similar applications. The proposed approach employs a deep convolutional autoencoder trained to reconstruct images of an unmodified board, but which remains unable to do the same for images showing modifications. By comparing the input image with its reconstruction, it is possible to segment anomalies and modifications in a pixel-wise manner. Experiments performed on a dataset built to represent real-world situations (and which we will make publicly available) show that our approach outperforms other state-of-the-art approaches for anomaly segmentation in the considered scenario, while producing comparable results on the popular MVTec-AD dataset for a more general object anomaly detection task.