Defect Detection in Photolithographic Patterns Using Deep Learning Models Trained on Synthetic Data

TL;DR

The real-time object detector YOLOv8 has the best mean average precision as compared to EfficientNet, 83%, and SSD, 77%, with the ability to detect smaller defects, and is reported the smallest defect size that can be detected reliably.

Abstract

In the photolithographic process vital to semiconductor manufacturing, various types of defects appear during EUV pattering. Due to ever-shrinking pattern size, these defects are extremely small and cause false or missed detection during inspection. Specifically, the lack of defect-annotated quality data with good representation of smaller defects has prohibited deployment of deep learning based defect detection models in fabrication lines. To resolve the problem of data unavailability, we artificially generate scanning electron microscopy (SEM) images of line patterns with known distribution of defects and autonomously annotate them. We then employ state-of-the-art object detection models to investigate defect detection performance as a function of defect size, much smaller than the pitch width. We find that the real-time object detector YOLOv8 has the best mean average precision of 96% as compared to EfficientNet, 83%, and SSD, 77%, with the ability to detect smaller defects. We report the smallest defect size that can be detected reliably. When tested on real SEM data, the YOLOv8 model correctly detected 84.6% of Bridge defects and 78.3% of Break defects across all relevant instances. These promising results suggest that synthetic data can be used as an alternative to real-world data in order to develop robust machine-learning models.

Figures (6)

• Figure 1: Overview of defect detection challenge
• Figure 2: Pseudocode to generate synthetic SEM images with various defects distributed uniformly.
• Figure 3: Examples of synthetic SEM images of lithographic line-space patterns with Break and Bridge defects. Enlarged regions indicate probable Bridge defects. Defects of various types and sizes are shown.
• Figure 4: True positive rate (Hit Rate) of YOLOv8, SSD, and EfficientNet models for Break and Bridge defects. Defect size is normalized by half-pitch width of the line pattern.
• Figure 5: Defect detection using YOLOv8 model trained on synthetic SEM images of lithographic line patterns with Break and Bridge defects. Detected defects are marked with boxes and arrows indicate undetected defects.