Classification by discrete optimization

Shmuel Peleg

doi:10.1016/0734-189X(84)90052-5

Classification by discrete optimization

Shmuel Peleg^*

^*Corresponding author for this work

The Rachel and Selim Benin School of Engineering and Computer Science

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

4 Scopus citations

Abstract

An approach to classification is described where an evaluation function is available. Deterministic classifications are evaluated by a heuristic function, and a special search procedure is applied to find a classification optimizing this function. A specific application to image segmentation is presented, including several examples. The major difference between this approach and previous optimization attempts is the use of deterministic ratter than probabilistic classifications.

Original language	English
Pages (from-to)	122-130
Number of pages	9
Journal	Computer Vision, Graphics, and Image Processing
Volume	25
Issue number	1
DOIs	https://doi.org/10.1016/0734-189X(84)90052-5
State	Published - Jan 1984

Access to Document

10.1016/0734-189X(84)90052-5

Cite this

@article{ccc2f09a801a4e4b9801a28191b2ea13,

title = "Classification by discrete optimization",

abstract = "An approach to classification is described where an evaluation function is available. Deterministic classifications are evaluated by a heuristic function, and a special search procedure is applied to find a classification optimizing this function. A specific application to image segmentation is presented, including several examples. The major difference between this approach and previous optimization attempts is the use of deterministic ratter than probabilistic classifications.",

author = "Shmuel Peleg",

year = "1984",

month = jan,

doi = "10.1016/0734-189X(84)90052-5",

language = "אנגלית",

volume = "25",

pages = "122--130",

journal = "Computer Vision, Graphics, and Image Processing",

issn = "0734-189X",

publisher = "Academic Press Inc.",

number = "1",

}

TY - JOUR

T1 - Classification by discrete optimization

AU - Peleg, Shmuel

PY - 1984/1

Y1 - 1984/1

N2 - An approach to classification is described where an evaluation function is available. Deterministic classifications are evaluated by a heuristic function, and a special search procedure is applied to find a classification optimizing this function. A specific application to image segmentation is presented, including several examples. The major difference between this approach and previous optimization attempts is the use of deterministic ratter than probabilistic classifications.

AB - An approach to classification is described where an evaluation function is available. Deterministic classifications are evaluated by a heuristic function, and a special search procedure is applied to find a classification optimizing this function. A specific application to image segmentation is presented, including several examples. The major difference between this approach and previous optimization attempts is the use of deterministic ratter than probabilistic classifications.

UR - https://www.scopus.com/pages/publications/0021643873

U2 - 10.1016/0734-189X(84)90052-5

DO - 10.1016/0734-189X(84)90052-5

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:0021643873

SN - 0734-189X

VL - 25

SP - 122

EP - 130

JO - Computer Vision, Graphics, and Image Processing

JF - Computer Vision, Graphics, and Image Processing

IS - 1

ER -

Classification by discrete optimization

Abstract

Access to Document

Other files and links

Fingerprint

Cite this