Parallel computable contour based feature strings for 2-D shape recognition

Its'hak Dinstein; Gad M. Landau

doi:10.1016/0167-8655(91)90413-G

Parallel computable contour based feature strings for 2-D shape recognition

Research output: Contribution to journal › Article › peer-review

Abstract

This letter presents parallel computable contour based feature strings for two-dimensional shape recognition. Parallel techniques are used for contour extraction and for computation of normalized contour based features independent of scale and rotation. The EREW PRAM architecture is considered, but the technique can be adapted to other parallel architectures. Illustrated examples are presented.

Original language	English
Pages (from-to)	299-306
Number of pages	8
Journal	Pattern Recognition Letters
Volume	12
Issue number	5
DOIs	https://doi.org/10.1016/0167-8655(91)90413-G
State	Published - May 1991
Externally published	Yes

Bibliographical note

Funding Information:
This work was supported in part by the New York State Science & Technology Foundation, Center for Advanced Technology in Telecommunications, Polytechnic University, Brooklyn, NY. * On leave from Ben-Gurion University, Beer Sheva, Israel. ** The research of this author was supported in part by NSF grant NSF-CCR-8908286.

Keywords

Parallel processing
shape

ASJC Scopus subject areas

Software
Signal Processing
Computer Vision and Pattern Recognition
Artificial Intelligence

Access to Document

10.1016/0167-8655(91)90413-G

Cite this

@article{94bb167117244758ae7162e6f2aa9a97,

title = "Parallel computable contour based feature strings for 2-D shape recognition",

abstract = "This letter presents parallel computable contour based feature strings for two-dimensional shape recognition. Parallel techniques are used for contour extraction and for computation of normalized contour based features independent of scale and rotation. The EREW PRAM architecture is considered, but the technique can be adapted to other parallel architectures. Illustrated examples are presented.",

keywords = "Parallel processing, shape",

author = "Its'hak Dinstein and Landau, {Gad M.}",

note = "Funding Information: This work was supported in part by the New York State Science & Technology Foundation, Center for Advanced Technology in Telecommunications, Polytechnic University, Brooklyn, NY. * On leave from Ben-Gurion University, Beer Sheva, Israel. ** The research of this author was supported in part by NSF grant NSF-CCR-8908286.",

year = "1991",

month = may,

doi = "10.1016/0167-8655(91)90413-G",

language = "English",

volume = "12",

pages = "299--306",

journal = "Pattern Recognition Letters",

issn = "0167-8655",

publisher = "Elsevier",

number = "5",

}

TY - JOUR

T1 - Parallel computable contour based feature strings for 2-D shape recognition

AU - Dinstein, Its'hak

AU - Landau, Gad M.

N1 - Funding Information: This work was supported in part by the New York State Science & Technology Foundation, Center for Advanced Technology in Telecommunications, Polytechnic University, Brooklyn, NY. * On leave from Ben-Gurion University, Beer Sheva, Israel. ** The research of this author was supported in part by NSF grant NSF-CCR-8908286.

PY - 1991/5

Y1 - 1991/5

N2 - This letter presents parallel computable contour based feature strings for two-dimensional shape recognition. Parallel techniques are used for contour extraction and for computation of normalized contour based features independent of scale and rotation. The EREW PRAM architecture is considered, but the technique can be adapted to other parallel architectures. Illustrated examples are presented.

AB - This letter presents parallel computable contour based feature strings for two-dimensional shape recognition. Parallel techniques are used for contour extraction and for computation of normalized contour based features independent of scale and rotation. The EREW PRAM architecture is considered, but the technique can be adapted to other parallel architectures. Illustrated examples are presented.

KW - Parallel processing

KW - shape

UR - http://www.scopus.com/inward/record.url?scp=0026300949&partnerID=8YFLogxK

U2 - 10.1016/0167-8655(91)90413-G

DO - 10.1016/0167-8655(91)90413-G

M3 - Article

AN - SCOPUS:0026300949

SN - 0167-8655

VL - 12

SP - 299

EP - 306

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

IS - 5

ER -

Parallel computable contour based feature strings for 2-D shape recognition

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this