用微调SAM模型快速精准分割AR/VR元件图像并提取关键尺寸。
Deep learning for fast segmentation and critical dimension metrology & characterization enabling AR/VR design and fabrication
- 微调预训练SAM模型，结合LoRA降低训练时间。
- 在多种电子显微图像上实现高精度二值化与关键尺寸提取。
- 适合芯片制造、光学器件设计等工业场景的快速分析需求。
定量分析显微图像对增强现实/虚拟现实（AR/VR）组件的设计与制造至关重要。然而，从复杂图像中分割感兴趣区域（ROIs）并提取关键尺寸（CDs）需新方法，如深度学习模型，以支持工艺、材料和器件优化的决策。本研究报告了使用多样化电子显微图像数据集对预训练的Segment Anything Model（SAM）进行微调，并采用低秩适配（LoRA）方法缩短训练时间、提升ROI提取精度。该模型具备良好的泛化能力，支持零样本学习，并可配合CD提取模型从分割结果中精确提取关键尺寸。我们成功实现了表面浮雕光栅（SRGs）和菲涅尔透镜横截面图像的二值化提取，涵盖单类与多类模式。进一步利用二值图像识别过渡点，辅助关键尺寸测量。结合微调分割模型与CD提取模型，显著提升了分析能力、数据获取速度与洞察效率，为多个工业应用带来实质性优势。
原文摘要 · Abstract (English)
Quantitative analysis of microscopy images is essential in the design and fabrication of components used in augmented reality/virtual reality (AR/VR) modules. However, segmenting regions of interest (ROIs) from these complex images and extracting critical dimensions (CDs) requires novel techniques, such as deep learning models which are key for actionable decisions on process, material and device optimization. In this study, we report on the fine-tuning of a pre-trained Segment Anything Model (SAM) using a diverse dataset of electron microscopy images. We employed methods such as low-rank adaptation (LoRA) to reduce training time and enhance the accuracy of ROI extraction. The model's ability to generalize to unseen images facilitates zero-shot learning and supports a CD extraction model that precisely extracts CDs from the segmented ROIs. We demonstrate the accurate extraction of binary images from cross-sectional images of surface relief gratings (SRGs) and Fresnel lenses in both single and multiclass modes. Furthermore, these binary images are used to identify transition points, aiding in the extraction of relevant CDs. The combined use of the fine-tuned segmentation model and the CD extraction model offers substantial advantages to various industrial applications by enhancing analytical capabilities, time to data and insights, and optimizing manufacturing processes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。