Automatic Defect Classification in Visual Inspection of Semiconductors Using Neural Networks

Keisuke KAMEYAMA; Yukio KOSUGI; Tatsuo OKAHASHI; Morishi IZUMITA

Automatic Defect Classification in Visual Inspection of Semiconductors Using Neural Networks

Keisuke KAMEYAMA, Yukio KOSUGI, Tatsuo OKAHASHI, Morishi IZUMITA

Full Text Views

0

Cite this

Summary :

An automatic defect classification system (ADC) for use in visual inspection of semiconductor wafers is introduced. The methods of extracting the defect features based on the human experts' knowledge, with their correlations with the defect classes are elucidated. As for the classifier, Hyperellipsoid Clustering Network (HCN) which is a layered network model employing second order discrimination borders in the feature space, is introduced. In the experiments using a collection of defect images, the HCNs are compared with the conventional multilayer perceptron networks. There, it is shown that the HCN's adaptive hyperellipsoidal discrimination borders are more suited for the problem. Also, the cluster encapsulation by the hyperellipsoidal border enables to determine rejection classes, which is also desirable when the system will be in actual use. The HCN with rejection achieves, an overall classification rate of 75% with an error rate of 18%, which can be considered equivalent to those of the human experts.

Publication: IEICE TRANSACTIONS on Information Vol.E81-D No.11 pp.1261-1271

Publication Date: 1998/11/25

Publicized

Online ISSN

DOI

Type of Manuscript

Category: Image Processing,Computer Graphics and Pattern Recognition

Cite this

Copy

Keisuke KAMEYAMA, Yukio KOSUGI, Tatsuo OKAHASHI, Morishi IZUMITA, "Automatic Defect Classification in Visual Inspection of Semiconductors Using Neural Networks" in IEICE TRANSACTIONS on Information, vol. E81-D, no. 11, pp. 1261-1271, November 1998, doi: .
Abstract: An automatic defect classification system (ADC) for use in visual inspection of semiconductor wafers is introduced. The methods of extracting the defect features based on the human experts' knowledge, with their correlations with the defect classes are elucidated. As for the classifier, Hyperellipsoid Clustering Network (HCN) which is a layered network model employing second order discrimination borders in the feature space, is introduced. In the experiments using a collection of defect images, the HCNs are compared with the conventional multilayer perceptron networks. There, it is shown that the HCN's adaptive hyperellipsoidal discrimination borders are more suited for the problem. Also, the cluster encapsulation by the hyperellipsoidal border enables to determine rejection classes, which is also desirable when the system will be in actual use. The HCN with rejection achieves, an overall classification rate of 75% with an error rate of 18%, which can be considered equivalent to those of the human experts.
URL: https://global.ieice.org/en_transactions/information/10.1587/e81-d_11_1261/_p

Copy

@ARTICLE{e81-d_11_1261,
author={Keisuke KAMEYAMA, Yukio KOSUGI, Tatsuo OKAHASHI, Morishi IZUMITA, },
journal={IEICE TRANSACTIONS on Information},
title={Automatic Defect Classification in Visual Inspection of Semiconductors Using Neural Networks},
year={1998},
volume={E81-D},
number={11},
pages={1261-1271},
abstract={An automatic defect classification system (ADC) for use in visual inspection of semiconductor wafers is introduced. The methods of extracting the defect features based on the human experts' knowledge, with their correlations with the defect classes are elucidated. As for the classifier, Hyperellipsoid Clustering Network (HCN) which is a layered network model employing second order discrimination borders in the feature space, is introduced. In the experiments using a collection of defect images, the HCNs are compared with the conventional multilayer perceptron networks. There, it is shown that the HCN's adaptive hyperellipsoidal discrimination borders are more suited for the problem. Also, the cluster encapsulation by the hyperellipsoidal border enables to determine rejection classes, which is also desirable when the system will be in actual use. The HCN with rejection achieves, an overall classification rate of 75% with an error rate of 18%, which can be considered equivalent to those of the human experts.},
keywords={},
doi={},
ISSN={},
month={November},}

Copy

TY - JOUR
TI - Automatic Defect Classification in Visual Inspection of Semiconductors Using Neural Networks
T2 - IEICE TRANSACTIONS on Information
SP - 1261
EP - 1271
AU - Keisuke KAMEYAMA
AU - Yukio KOSUGI
AU - Tatsuo OKAHASHI
AU - Morishi IZUMITA
PY - 1998
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E81-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 1998
AB - An automatic defect classification system (ADC) for use in visual inspection of semiconductor wafers is introduced. The methods of extracting the defect features based on the human experts' knowledge, with their correlations with the defect classes are elucidated. As for the classifier, Hyperellipsoid Clustering Network (HCN) which is a layered network model employing second order discrimination borders in the feature space, is introduced. In the experiments using a collection of defect images, the HCNs are compared with the conventional multilayer perceptron networks. There, it is shown that the HCN's adaptive hyperellipsoidal discrimination borders are more suited for the problem. Also, the cluster encapsulation by the hyperellipsoidal border enables to determine rejection classes, which is also desirable when the system will be in actual use. The HCN with rejection achieves, an overall classification rate of 75% with an error rate of 18%, which can be considered equivalent to those of the human experts.
ER -