Quantification and abstraction: low level tokens for object extraction

Amnon Meisels; Ofer Hason; Hedva Hess

doi:10.1016/0262-8856(91)90009-E

Quantification and abstraction: low level tokens for object extraction

Amnon Meisels, Ofer Hason, Hedva Hess

Department of Computer Science

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

1 Scopus citations

Abstract

A paradigm for the abstraction of digital data into symbolic tokens that take part in object extraction is described. The low level processes of abstraction deal with the construction of tokens, and with knowledgebased choice of thresholds for all quantities that are involved in object extraction. These processes that transform digital data into symbolic, abstract tokens and descriptions are controlled by a higher level symbolic process that uses reasoning. A detailed description is presented of the generation and correction of two kinds of intermediate level tokens: line segments and uniform blobs. The construction of contextual segments from these tokens in the experiment is based on their symbolic description, as well as on the adaptive and symbolic description of all relevant quantities.

Original language	English
Pages (from-to)	151-159
Number of pages	9
Journal	Image and Vision Computing
Volume	9
Issue number	3
DOIs	https://doi.org/10.1016/0262-8856(91)90009-E
State	Published - 1 Jan 1991

Keywords

Image interpretation
intermediate-level vision image tokens

ASJC Scopus subject areas

Signal Processing
Computer Vision and Pattern Recognition

Access to Document

10.1016/0262-8856(91)90009-E

Cite this

@article{196f2bcff5eb44f7a931c271c60894c2,

title = "Quantification and abstraction: low level tokens for object extraction",

abstract = "A paradigm for the abstraction of digital data into symbolic tokens that take part in object extraction is described. The low level processes of abstraction deal with the construction of tokens, and with knowledgebased choice of thresholds for all quantities that are involved in object extraction. These processes that transform digital data into symbolic, abstract tokens and descriptions are controlled by a higher level symbolic process that uses reasoning. A detailed description is presented of the generation and correction of two kinds of intermediate level tokens: line segments and uniform blobs. The construction of contextual segments from these tokens in the experiment is based on their symbolic description, as well as on the adaptive and symbolic description of all relevant quantities.",

keywords = "Image interpretation, intermediate-level vision image tokens",

author = "Amnon Meisels and Ofer Hason and Hedva Hess",

year = "1991",

month = jan,

day = "1",

doi = "10.1016/0262-8856(91)90009-E",

language = "English",

volume = "9",

pages = "151--159",

journal = "Image and Vision Computing",

issn = "0262-8856",

publisher = "Elsevier Ltd.",

number = "3",

}

TY - JOUR

T1 - Quantification and abstraction

T2 - low level tokens for object extraction

AU - Meisels, Amnon

AU - Hason, Ofer

AU - Hess, Hedva

PY - 1991/1/1

Y1 - 1991/1/1

N2 - A paradigm for the abstraction of digital data into symbolic tokens that take part in object extraction is described. The low level processes of abstraction deal with the construction of tokens, and with knowledgebased choice of thresholds for all quantities that are involved in object extraction. These processes that transform digital data into symbolic, abstract tokens and descriptions are controlled by a higher level symbolic process that uses reasoning. A detailed description is presented of the generation and correction of two kinds of intermediate level tokens: line segments and uniform blobs. The construction of contextual segments from these tokens in the experiment is based on their symbolic description, as well as on the adaptive and symbolic description of all relevant quantities.

AB - A paradigm for the abstraction of digital data into symbolic tokens that take part in object extraction is described. The low level processes of abstraction deal with the construction of tokens, and with knowledgebased choice of thresholds for all quantities that are involved in object extraction. These processes that transform digital data into symbolic, abstract tokens and descriptions are controlled by a higher level symbolic process that uses reasoning. A detailed description is presented of the generation and correction of two kinds of intermediate level tokens: line segments and uniform blobs. The construction of contextual segments from these tokens in the experiment is based on their symbolic description, as well as on the adaptive and symbolic description of all relevant quantities.

KW - Image interpretation

KW - intermediate-level vision image tokens

UR - http://www.scopus.com/inward/record.url?scp=0026170005&partnerID=8YFLogxK

U2 - 10.1016/0262-8856(91)90009-E

DO - 10.1016/0262-8856(91)90009-E

M3 - Article

AN - SCOPUS:0026170005

SN - 0262-8856

VL - 9

SP - 151

EP - 159

JO - Image and Vision Computing

JF - Image and Vision Computing

IS - 3

ER -

Quantification and abstraction: low level tokens for object extraction

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this