Defect Detection Approaches Based on Simulated Reference Image

TL;DR

This paper explores the use of simulated reference images to enhance defect and anomaly detection in SEM semiconductor images and natural images, demonstrating improved performance over real references due to reduced noise and better alignment.

Contribution

The study introduces methods to effectively incorporate simulated reference images into various defect detection techniques, improving accuracy and robustness.

Findings

Simulated references outperform real references in defect detection accuracy.

Reduced noise and geometric variations in simulated references improve detection performance.

Simulated references provide better alignment with defect backgrounds, enhancing detection results.

Abstract

This work is addressing the problem of defect anomaly detection based on a clean reference image. Specifically, we focus on SEM semiconductor defects in addition to several natural image anomalies. There are well-known methods to create a simulation of an artificial reference image by its defect specimen. In this work, we introduce several applications for this capability, that the simulated reference is beneficial for improving their results. Among these defect detection methods are classic computer vision applied on difference-image, supervised deep-learning (DL) based on human labels, and unsupervised DL which is trained on feature-level patterns of normal reference images. We show in this study how to incorporate correctly the simulated reference image for these defect and anomaly detection applications. As our experiment demonstrates, simulated reference achieves higher performance than the real reference of an image of a defect and anomaly. This advantage of simulated reference occurs mainly due to the less noise and geometric variations together with better alignment and registration to the original defect background.