In this study, we applied the PointRend (Point-based Rendering) method to semiconductor defect segmentation. PointRend is an iterative segmentation algorithm inspired by image rendering in computer graphics, a new image segmentation method that can generate high-resolution segmentation masks. It can also be flexibly integrated into common instance segmentation meta-architecture such as Mask-RCNN and semantic meta-architecture such as FCN. We implemented a model, termed as SEMI-PointRend, to generate precise segmentation masks by applying the PointRend neural network module. In this paper, we focus on comparing the defect segmentation predictions of SEMI-PointRend and Mask-RCNN for various defect types (line-collapse, single bridge, thin bridge, multi bridge non-horizontal). We show that SEMI-PointRend can outperforms Mask R-CNN by up to 18.8% in terms of segmentation mean average precision.
@article{arxiv.2302.09569,
title = {SEMI-PointRend: Improved Semiconductor Wafer Defect Classification and Segmentation as Rendering},
author = {MinJin Hwang and Bappaditya Dey and Enrique Dehaerne and Sandip Halder and Young-han Shin},
journal= {arXiv preprint arXiv:2302.09569},
year = {2023}
}
Comments
7 pages, 6 figures, 5 tables. To be published by SPIE in the proceedings of Metrology, Inspection, and Process Control XXXVII