Deep learning for fast segmentation and critical dimension metrology & characterization enabling AR/VR design and fabrication

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chaudhary, Kundan, Shaar, Subhei, Muthinti, Raja
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916405587214336
author Chaudhary, Kundan
Shaar, Subhei
Muthinti, Raja
author_facet Chaudhary, Kundan
Shaar, Subhei
Muthinti, Raja
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2409_13951
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deep learning for fast segmentation and critical dimension metrology & characterization enabling AR/VR design and fabrication
Chaudhary, Kundan
Shaar, Subhei
Muthinti, Raja
Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
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.
title Deep learning for fast segmentation and critical dimension metrology & characterization enabling AR/VR design and fabrication
topic Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2409.13951