High Dimensional Data Decomposition for Anomaly Detection of Textured Images

TL;DR

This paper introduces a novel texture basis integrated smooth decomposition (TBSD) method for efficient and accurate anomaly detection in textured images, overcoming limitations of traditional methods especially with small datasets.

Contribution

The paper presents a new TBSD approach that effectively learns texture bases and improves anomaly detection accuracy in textured images with limited data.

Findings

Outperforms benchmark methods in accuracy

Requires smaller training datasets

Reduces misidentification of textures

Abstract

In the realm of diverse high-dimensional data, images play a significant role across various processes of manufacturing systems where efficient image anomaly detection has emerged as a core technology of utmost importance. However, when applied to textured defect images, conventional anomaly detection methods have limitations including non-negligible misidentification, low robustness, and excessive reliance on large-scale and structured datasets. This paper proposes a texture basis integrated smooth decomposition (TBSD) approach, which is targeted at efficient anomaly detection in textured images with smooth backgrounds and sparse anomalies. Mathematical formulation of quasi-periodicity and its theoretical properties are investigated for image texture estimation. TBSD method consists of two principal processes: the first process learns the texture basis functions to effectively extract quasi-periodic texture patterns; the subsequent anomaly detection process utilizes that texture basis as prior knowledge to prevent texture misidentification and capture potential anomalies with high accuracy.The proposed method surpasses benchmarks with less misidentification, smaller training dataset requirement, and superior anomaly detection performance on both simulation and real-world datasets.