High Dimensional Data Decomposition for Anomaly Detection of Textured Images
This work addresses efficient anomaly detection for textured images in manufacturing systems, offering improvements over conventional methods but is incremental in nature.
The paper tackled the problem of anomaly detection in textured images by proposing a texture basis integrated smooth decomposition (TBSD) approach, which reduced misidentification, required smaller training datasets, and achieved superior performance on simulation and real-world datasets.
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.