Context-based automated defect classification system using multiple morphological masks
Abstract
Automatic detection of defects during the fabrication of semiconductor wafers is largely automated, but the classification of those defects is still performed manually by technicians. This invention includes novel digital image analysis techniques that generate unique feature vector descriptions of semiconductor defects as well as classifiers that use these descriptions to automatically categorize the defects into one of a set of pre-defined classes. Feature extraction techniques based on multiple-focus images, multiple-defect mask images, and segmented semiconductor wafer images are used to create unique feature-based descriptions of the semiconductor defects. These feature-based defect descriptions are subsequently classified by a defect classifier into categories that depend on defect characteristics and defect contextual information, that is, the semiconductor process layer(s) with which the defect comes in contact. At the heart of the system is a knowledge database that stores and distributes historical semiconductor wafer and defect data to guide the feature extraction and classification processes. In summary, this invention takes as its input a set of images containing semiconductor defect information, and generates as its output a classification for the defect that describes not only the defect itself, but also the location of that defect with respect to the semiconductor process layers.
- Inventors:
-
- Knoxville, TN
- Lubbock, TX
- Issue Date:
- Research Org.:
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
- OSTI Identifier:
- 874768
- Patent Number(s):
- 6456899
- Assignee:
- UT-Battelle, LLC (Oak Ridge, TN)
- Patent Classifications (CPCs):
-
G - PHYSICS G03 - PHOTOGRAPHY G03F - PHOTOMECHANICAL PRODUCTION OF TEXTURED OR PATTERNED SURFACES, e.g. FOR PRINTING, FOR PROCESSING OF SEMICONDUCTOR DEVICES
G - PHYSICS G05 - CONTROLLING G05B - CONTROL OR REGULATING SYSTEMS IN GENERAL
- DOE Contract Number:
- AC05-96OR22464
- Resource Type:
- Patent
- Country of Publication:
- United States
- Language:
- English
- Subject:
- context-based; automated; defect; classification; multiple; morphological; masks; automatic; detection; defects; fabrication; semiconductor; wafers; performed; manually; technicians; novel; digital; image; analysis; techniques; generate; unique; feature; vector; descriptions; classifiers; automatically; categorize; set; pre-defined; extraction; based; multiple-focus; images; multiple-defect; mask; segmented; wafer; create; feature-based; subsequently; classified; classifier; categories; depend; characteristics; contextual; information; process; layers; contact; heart; knowledge; database; stores; distributes; historical; data; guide; processes; takes; input; containing; generates; output; describes; location; digital image; /700/706/
Citation Formats
Gleason, Shaun S, Hunt, Martin A, and Sari-Sarraf, Hamed. Context-based automated defect classification system using multiple morphological masks. United States: N. p., 2002.
Web.
Gleason, Shaun S, Hunt, Martin A, & Sari-Sarraf, Hamed. Context-based automated defect classification system using multiple morphological masks. United States.
Gleason, Shaun S, Hunt, Martin A, and Sari-Sarraf, Hamed. Tue .
"Context-based automated defect classification system using multiple morphological masks". United States. https://www.osti.gov/servlets/purl/874768.
@article{osti_874768,
title = {Context-based automated defect classification system using multiple morphological masks},
author = {Gleason, Shaun S and Hunt, Martin A and Sari-Sarraf, Hamed},
abstractNote = {Automatic detection of defects during the fabrication of semiconductor wafers is largely automated, but the classification of those defects is still performed manually by technicians. This invention includes novel digital image analysis techniques that generate unique feature vector descriptions of semiconductor defects as well as classifiers that use these descriptions to automatically categorize the defects into one of a set of pre-defined classes. Feature extraction techniques based on multiple-focus images, multiple-defect mask images, and segmented semiconductor wafer images are used to create unique feature-based descriptions of the semiconductor defects. These feature-based defect descriptions are subsequently classified by a defect classifier into categories that depend on defect characteristics and defect contextual information, that is, the semiconductor process layer(s) with which the defect comes in contact. At the heart of the system is a knowledge database that stores and distributes historical semiconductor wafer and defect data to guide the feature extraction and classification processes. In summary, this invention takes as its input a set of images containing semiconductor defect information, and generates as its output a classification for the defect that describes not only the defect itself, but also the location of that defect with respect to the semiconductor process layers.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2002},
month = {1}
}
Works referenced in this record:
Automatic classification of defects in semiconductor devices
conference, June 1990
- Dralla, John R.; Hoff, John C.
- Microlithography '90, 4-9 Mar, San Jose, SPIE Proceedings
Nonlinear filter derived from topological image features
conference, September 1990
- Jatko, William B.; Hunt, Martin A.; Tobin, Jr., Kenneth W.
- Orlando '90, 16-20 April, SPIE Proceedings
Subpixel measurement of image features based on paraboloid surface fit
conference, March 1991
- Gleason, Shaun S.; Hunt, Martin A.; Jatko, William B.
- Fibers '91, Boston, MA, SPIE Proceedings
Automatic defect classification system for semiconductor wafers
conference, May 1993
- Sherman, Rivi; Tirosh, Ehud; Smilansky, Zeev
- IS&T/SPIE's Symposium on Electronic Imaging: Science and Technology, SPIE Proceedings