Anomaly Detection of Defect using Energy of Point Pattern Features within Random Finite Set Framework

TL;DR

This paper introduces a novel anomaly detection method for industrial defect identification using point pattern features modeled as a random finite set, leveraging transfer learning and RFS energy to improve robustness and performance.

Contribution

It is the first to use transfer learning of local features within an RFS framework for defect detection, introducing RFS energy as an anomaly score.

Findings

Outperforms state-of-the-art methods on MVTec AD dataset.

Effective in few-shot learning scenarios.

Robust against lighting and viewpoint variations.

Abstract

In this paper, we propose an efficient approach for industrial defect detection that is modeled based on anomaly detection using point pattern data. Most recent works use \textit{global features} for feature extraction to summarize image content. However, global features are not robust against lighting and viewpoint changes and do not describe the image's geometrical information to be fully utilized in the manufacturing industry. To the best of our knowledge, we are the first to propose using transfer learning of local/point pattern features to overcome these limitations and capture geometrical information of the image regions. We model these local/point pattern features as a random finite set (RFS). In addition we propose RFS energy, in contrast to RFS likelihood as anomaly score. The similarity distribution of point pattern features of the normal sample has been modeled as a multivariate Gaussian. Parameters learning of the proposed RFS energy does not require any heavy computation. We evaluate the proposed approach on the MVTec AD dataset, a multi-object defect detection dataset. Experimental results show the outstanding performance of our proposed approach compared to the state-of-the-art methods, and the proposed RFS energy outperforms the state-of-the-art in the few shot learning settings.