Model-based partial shape recognition using contour curvature and affine transformation

Frank Y. Shih; Pingchang Yeh

Model-based partial shape recognition using contour curvature and affine transformation

Frank Y. Shih, Pingchang Yeh

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

The authors present a novel technique for recognizing partially obscured and overlapping objects by using the contour curvature and affine transformation. This technique is based on the use of an invariant attribute of an object, called a footprint, for the purpose of hashing. The recognition strategy is to match the given contour curve against all model objects and select the best matching. The recognition procedures are divided into reading each object picture, retrieving a footprint, building a model objects database, finding break points, and matching. Associated techniques, such as border tracking with chain code, setting a footprint hashing table, and connecting an orientational linked list, are also discussed.

Original language	English (US)
Title of host publication	Proc First Int Conf Syst Integr ICSI 90
Publisher	Publ by IEEE
Pages	294-301
Number of pages	8
ISBN (Print)	0818690275
State	Published - 1990
Event	Proceedings of the First International Conference on Systems Integration - ICSI '90 - Morristown, NJ, USA Duration: Apr 23 1990 → Apr 26 1990

Publication series

Name	Proc First Int Conf Syst Integr ICSI 90

Other

Other	Proceedings of the First International Conference on Systems Integration - ICSI '90
City	Morristown, NJ, USA
Period	4/23/90 → 4/26/90

All Science Journal Classification (ASJC) codes

General Engineering

Cite this

@inproceedings{572446a42ef7498d95bf574bc6b82f70,

title = "Model-based partial shape recognition using contour curvature and affine transformation",

abstract = "The authors present a novel technique for recognizing partially obscured and overlapping objects by using the contour curvature and affine transformation. This technique is based on the use of an invariant attribute of an object, called a footprint, for the purpose of hashing. The recognition strategy is to match the given contour curve against all model objects and select the best matching. The recognition procedures are divided into reading each object picture, retrieving a footprint, building a model objects database, finding break points, and matching. Associated techniques, such as border tracking with chain code, setting a footprint hashing table, and connecting an orientational linked list, are also discussed.",

author = "Shih, {Frank Y.} and Pingchang Yeh",

year = "1990",

language = "English (US)",

isbn = "0818690275",

series = "Proc First Int Conf Syst Integr ICSI 90",

publisher = "Publ by IEEE",

pages = "294--301",

booktitle = "Proc First Int Conf Syst Integr ICSI 90",

note = "Proceedings of the First International Conference on Systems Integration - ICSI '90 ; Conference date: 23-04-1990 Through 26-04-1990",

}

TY - GEN

T1 - Model-based partial shape recognition using contour curvature and affine transformation

AU - Shih, Frank Y.

AU - Yeh, Pingchang

PY - 1990

Y1 - 1990

N2 - The authors present a novel technique for recognizing partially obscured and overlapping objects by using the contour curvature and affine transformation. This technique is based on the use of an invariant attribute of an object, called a footprint, for the purpose of hashing. The recognition strategy is to match the given contour curve against all model objects and select the best matching. The recognition procedures are divided into reading each object picture, retrieving a footprint, building a model objects database, finding break points, and matching. Associated techniques, such as border tracking with chain code, setting a footprint hashing table, and connecting an orientational linked list, are also discussed.

AB - The authors present a novel technique for recognizing partially obscured and overlapping objects by using the contour curvature and affine transformation. This technique is based on the use of an invariant attribute of an object, called a footprint, for the purpose of hashing. The recognition strategy is to match the given contour curve against all model objects and select the best matching. The recognition procedures are divided into reading each object picture, retrieving a footprint, building a model objects database, finding break points, and matching. Associated techniques, such as border tracking with chain code, setting a footprint hashing table, and connecting an orientational linked list, are also discussed.

UR - http://www.scopus.com/inward/record.url?scp=0025564559&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025564559&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0025564559

SN - 0818690275

T3 - Proc First Int Conf Syst Integr ICSI 90

SP - 294

EP - 301

BT - Proc First Int Conf Syst Integr ICSI 90

PB - Publ by IEEE

T2 - Proceedings of the First International Conference on Systems Integration - ICSI '90

Y2 - 23 April 1990 through 26 April 1990

ER -

Model-based partial shape recognition using contour curvature and affine transformation

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this