🤖 AI Summary
High-quality, physically plausible annotations for lithographic defect detection are scarce, hindering robust AI-based quality inspection. Method: We propose a design-driven, physics-constrained defect image generation framework: defects are synthetically placed on layout patterns using mathematical morphology; realistic images are acquired via DMD-based lithography and optical microscopy; and corresponding pixel-level contour masks are generated synchronously. Contribution/Results: We introduce LithoDefect-1K—the first open-source lithographic defect dataset comprising 13,365 instances across four defect types, spanning 3,530 images. Our paradigm enables controllable, interpretable, and high-fidelity annotation generation. Evaluated on Mask R-CNN, it achieves mean AP@0.5 of 78.6%–84.2%, outperforming Faster R-CNN by 34%–42%, thereby demonstrating substantial performance gains from physics-guided data synthesis for AI-powered inspection.
📝 Abstract
The efficacy of Artificial Intelligence (AI) in micro/nano manufacturing is fundamentally constrained by the scarcity of high-quality and physically grounded training data for defect inspection. Lithography defect data from semiconductor industry are rarely accessible for research use, resulting in a shortage of publicly available datasets. To address this bottleneck in lithography, this study proposes a novel methodology for generating large-scale, physically valid defect datasets with pixel-level annotations. The framework begins with the ab initio synthesis of defect layouts using controllable, physics-constrained mathematical morphology operations (erosion and dilation) applied to the original design-level layout. These synthesized layouts, together with their defect-free counterparts, are fabricated into physical samples via high-fidelity digital micromirror device (DMD)-based lithography. Optical micrographs of the synthesized defect samples and their defect-free references are then compared to create consistent defect delineation annotations. Using this methodology, we constructed a comprehensive dataset of 3,530 Optical micrographs containing 13,365 annotated defect instances including four classes: bridge, burr, pinch, and contamination. Each defect instance is annotated with a pixel-accurate segmentation mask, preserving full contour and geometry. The segmentation-based Mask R-CNN achieves AP@0.5 of 0.980, 0.965, and 0.971, compared with 0.740, 0.719, and 0.717 for Faster R-CNN on bridge, burr, and pinch classes, representing a mean AP@0.5 improvement of approximately 34%. For the contamination class, Mask R-CNN achieves an AP@0.5 roughly 42% higher than Faster R-CNN. These consistent gains demonstrate that our proposed methodology to generate defect datasets with pixel-level annotations is feasible for robust AI-based Measurement/Inspection (MI) in semiconductor fabrication.