Unsupervised Anomaly Detection Using Diffusion Trend Analysis for Display Inspection

TL;DR

This paper introduces a novel anomaly detection method for display inspection that analyzes reconstruction trends based on degradation levels, overcoming limitations of existing diffusion-based approaches and reducing false positives.

Contribution

The proposed method effectively detects anomalies by analyzing reconstruction trends, addressing noise parameter selection issues and fluctuation problems in diffusion-based models.

Findings

Improved detection accuracy in display inspection

Reduced false positives due to fluctuation handling

Effective analysis of degradation-dependent reconstruction trends

Abstract

Reconstruction-based anomaly detection via denoising diffusion model has limitations in determining appropriate noise parameters that can degrade anomalies while preserving normal characteristics. Also, normal regions can fluctuate considerably during reconstruction, resulting in false detection. In this paper, we propose a method to detect anomalies by analysis of reconstruction trend depending on the degree of degradation, effectively solving the both problems that impede practical application in display inspection.