Presentation 2005-09-21
Recognition Method of Minute Defect Based on Comparison to Statistical Pattern and Outlier Detection on Feature Space
Kaoru SAKAI, Shunji MAEDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Reductions of the noise caused by the pattern shape difference and the sampling errors are essential to recognize a minute defect on the complicated multilayer patterns on wafers. We propose a highly sensitive comparison inspection method with noise reducion. We generate a statistical pattern from plural repetitive patterns and we compare the detected image with the statistical pattern. The grayscale is converted so that the grayscales of the two images are matched and the difference is compressed using Maharanobis distance according to the grayscale fluctuation. This new method can detect small defects without the influence of pattern roughness.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Comparison inspection / Defect recognition / Statistical outlier detection
Paper # NLC2005-26,PRMU2005-53
Date of Issue

Conference Information
Committee NLC
Conference Date 2005/9/14(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 Natural Language Understanding and Models of Communication (NLC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Recognition Method of Minute Defect Based on Comparison to Statistical Pattern and Outlier Detection on Feature Space
Sub Title (in English)
Keyword(1) Comparison inspection
Keyword(2) Defect recognition
Keyword(3) Statistical outlier detection
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 2005-09-21
Paper # NLC2005-26,PRMU2005-53
Volume (vol) vol.105
Number (no) 299
Page pp.pp.-
#Pages 6
Date of Issue