A new model-based approach for industrial visual inspection

Yung-Nien Sun, Ching Tsorng Tsai

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Two critical steps in industrial visual inspection are to design a flexible representation scheme and to match it with an effective inspection algorithm. Good representation and inspection algorithms can drastically speed up the subsequent matching process, and strengthen the feasibility of complicated on-line inspection. A novel pictorial representation called pattern attributed hypergraph (PAHG) and a new structural inspection algorithm are presented. The PAHG is used to describe the pictorial information of an input pattern, which includes attributed nodes, connectivity between nodes (intra-relations), regional primitives, and neighborhood relations between regions (inter-relations). The new structural inspection algorithm based on PAHG is proposed to match the inspected scene with the model efficiently. Consequently, the amount of matching computation is significantly reduced to roughly 1/k3 of the currently available method (Darwish and Jain, IEEE Trans. Pattern Analysis Mach. Intell. 10, 56-68 (1988)), where k is the number of partitioned regions. The theoretical analysis and experimental results have shown the superiority of the proposed method.

Original languageEnglish
Pages (from-to)1327-1336
Number of pages10
JournalPattern Recognition
Volume25
Issue number11
DOIs
Publication statusPublished - 1992 Jan 1

Fingerprint

Inspection
Mach number

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Sun, Yung-Nien ; Tsai, Ching Tsorng. / A new model-based approach for industrial visual inspection. In: Pattern Recognition. 1992 ; Vol. 25, No. 11. pp. 1327-1336.
@article{48f65c2289514da9b93ab315eccc8e41,
title = "A new model-based approach for industrial visual inspection",
abstract = "Two critical steps in industrial visual inspection are to design a flexible representation scheme and to match it with an effective inspection algorithm. Good representation and inspection algorithms can drastically speed up the subsequent matching process, and strengthen the feasibility of complicated on-line inspection. A novel pictorial representation called pattern attributed hypergraph (PAHG) and a new structural inspection algorithm are presented. The PAHG is used to describe the pictorial information of an input pattern, which includes attributed nodes, connectivity between nodes (intra-relations), regional primitives, and neighborhood relations between regions (inter-relations). The new structural inspection algorithm based on PAHG is proposed to match the inspected scene with the model efficiently. Consequently, the amount of matching computation is significantly reduced to roughly 1/k3 of the currently available method (Darwish and Jain, IEEE Trans. Pattern Analysis Mach. Intell. 10, 56-68 (1988)), where k is the number of partitioned regions. The theoretical analysis and experimental results have shown the superiority of the proposed method.",
author = "Yung-Nien Sun and Tsai, {Ching Tsorng}",
year = "1992",
month = "1",
day = "1",
doi = "10.1016/0031-3203(92)90145-9",
language = "English",
volume = "25",
pages = "1327--1336",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "11",

}

A new model-based approach for industrial visual inspection. / Sun, Yung-Nien; Tsai, Ching Tsorng.

In: Pattern Recognition, Vol. 25, No. 11, 01.01.1992, p. 1327-1336.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A new model-based approach for industrial visual inspection

AU - Sun, Yung-Nien

AU - Tsai, Ching Tsorng

PY - 1992/1/1

Y1 - 1992/1/1

N2 - Two critical steps in industrial visual inspection are to design a flexible representation scheme and to match it with an effective inspection algorithm. Good representation and inspection algorithms can drastically speed up the subsequent matching process, and strengthen the feasibility of complicated on-line inspection. A novel pictorial representation called pattern attributed hypergraph (PAHG) and a new structural inspection algorithm are presented. The PAHG is used to describe the pictorial information of an input pattern, which includes attributed nodes, connectivity between nodes (intra-relations), regional primitives, and neighborhood relations between regions (inter-relations). The new structural inspection algorithm based on PAHG is proposed to match the inspected scene with the model efficiently. Consequently, the amount of matching computation is significantly reduced to roughly 1/k3 of the currently available method (Darwish and Jain, IEEE Trans. Pattern Analysis Mach. Intell. 10, 56-68 (1988)), where k is the number of partitioned regions. The theoretical analysis and experimental results have shown the superiority of the proposed method.

AB - Two critical steps in industrial visual inspection are to design a flexible representation scheme and to match it with an effective inspection algorithm. Good representation and inspection algorithms can drastically speed up the subsequent matching process, and strengthen the feasibility of complicated on-line inspection. A novel pictorial representation called pattern attributed hypergraph (PAHG) and a new structural inspection algorithm are presented. The PAHG is used to describe the pictorial information of an input pattern, which includes attributed nodes, connectivity between nodes (intra-relations), regional primitives, and neighborhood relations between regions (inter-relations). The new structural inspection algorithm based on PAHG is proposed to match the inspected scene with the model efficiently. Consequently, the amount of matching computation is significantly reduced to roughly 1/k3 of the currently available method (Darwish and Jain, IEEE Trans. Pattern Analysis Mach. Intell. 10, 56-68 (1988)), where k is the number of partitioned regions. The theoretical analysis and experimental results have shown the superiority of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=0026944660&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026944660&partnerID=8YFLogxK

U2 - 10.1016/0031-3203(92)90145-9

DO - 10.1016/0031-3203(92)90145-9

M3 - Article

VL - 25

SP - 1327

EP - 1336

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 11

ER -