Presentation 2006-09-08
LSI wafer inspection method using recursive splitting of feature space
Kaoru SAKAI, Shunji MAEDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) To detect minute defects on the complicated multilayer patterns of semiconductor wafers, effective inspection algorithm is essential. There are multiple dies on a wafer that are designed to be same. We propose a highly sensitive die-to-die comparison algorithm that can recognize the defects buried in the pattern variation noise due to process fluctuation. This comparison algorithm is based on recursive splitting of feature space. The method has the same procedures as the regression tree. The images to be compared are separated into several regions by the recursive splitting of feature space. For each region, defects are recognized as statistical outliers in the scattergram of the images. The effectiveness of the method is confirmed through the experiments.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) inspection / defect / regression tree / feature space / scattergram / statistical outlier
Paper # PRMU2006-69
Date of Issue

Conference Information
Committee PRMU
Conference Date 2006/9/1(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) LSI wafer inspection method using recursive splitting of feature space
Sub Title (in English)
Keyword(1) inspection
Keyword(2) defect
Keyword(3) regression tree
Keyword(4) feature space
Keyword(5) scattergram
Keyword(6) statistical outlier
1st Author's Name Kaoru SAKAI
1st Author's Affiliation Hitachi, LTD., Production Engineering Research Laboratory()
2nd Author's Name Shunji MAEDA
2nd Author's Affiliation Hitachi, LTD., Production Engineering Research Laboratory
Date 2006-09-08
Paper # PRMU2006-69
Volume (vol) vol.106
Number (no) 229
Page pp.pp.-
#Pages 8
Date of Issue