TY - JOUR
T1 - Content-based image retrieval for semiconductor process characterization
AU - Tobin, Kenneth W.
AU - Karnowski, Thomas P.
AU - Arrowood, Lloyd F.
AU - Ferrell, Regina K.
AU - Goddard, James S.
AU - Lakhani, Fred
PY - 2002/7
Y1 - 2002/7
N2 - Image data management in the semiconductor manufacturing environment is becoming more problematic as the size of silicon wafers continues to increase, while the dimension of critical features continues to shrink. Fabricators rely on a growing host of image-generating inspection tools to monitor complex device manufacturing processes. These inspection tools include optical and laser scattering microscopy, confocal microscopy, scanning electron microscopy, and atomic force microscopy. The number of im- ages that are being generated are on the order of 20,000 to 30,000 each week in some fabrication facilities today. Manufacturers currently maintain on the order of 500,000 images in their data management systems for extended periods of time. Gleaning the historical value from these large image repositories for yield improvement is difficult to accomplish using the standard database methods currently associated with these data sets (e.g., performing queries based on time and date, lot numbers, wafer iden- tification numbers, etc.). Researchers at the Oak Ridge National Laboratory have developed and tested a content-based image retrieval technology that is specific to manufacturing environments. In this paper, we describe the feature representation of semi- conductor defect images along with methods of indexing and retrieval, and results from initial field-testing in the semiconductor manufacturing environment.
AB - Image data management in the semiconductor manufacturing environment is becoming more problematic as the size of silicon wafers continues to increase, while the dimension of critical features continues to shrink. Fabricators rely on a growing host of image-generating inspection tools to monitor complex device manufacturing processes. These inspection tools include optical and laser scattering microscopy, confocal microscopy, scanning electron microscopy, and atomic force microscopy. The number of im- ages that are being generated are on the order of 20,000 to 30,000 each week in some fabrication facilities today. Manufacturers currently maintain on the order of 500,000 images in their data management systems for extended periods of time. Gleaning the historical value from these large image repositories for yield improvement is difficult to accomplish using the standard database methods currently associated with these data sets (e.g., performing queries based on time and date, lot numbers, wafer iden- tification numbers, etc.). Researchers at the Oak Ridge National Laboratory have developed and tested a content-based image retrieval technology that is specific to manufacturing environments. In this paper, we describe the feature representation of semi- conductor defect images along with methods of indexing and retrieval, and results from initial field-testing in the semiconductor manufacturing environment.
KW - Approximate nearest neighbors.
KW - Automatic defect classification
KW - Content-based image retrieval
KW - Image indexing
KW - Semiconductor manufacturing
UR - http://www.scopus.com/inward/record.url?scp=0036665620&partnerID=8YFLogxK
U2 - 10.1155/S1110865702203017
DO - 10.1155/S1110865702203017
M3 - Article
AN - SCOPUS:0036665620
SN - 1110-8657
VL - 2002
SP - 704
EP - 713
JO - Eurasip Journal on Applied Signal Processing
JF - Eurasip Journal on Applied Signal Processing
IS - 7
ER -