2-D SCENE ANALYSIS USING SPLIT-LEVEL RELAXATION.

Tom Henderson, Ashok K Samal

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

A new method is presented for applying multiple semantic constraints based on discrete relaxation. A separate graph is maintained for each constraint relation and is used in parallel to achieve a consistent labeling. This permits both local and global analysis without recourse to complete graphs. Here 'local' means with respect to particular constraint graph and thus actually includes global spatial relations on the features; e. g. , parallel edges on an object will be neighbors in the parallel constraint graph even though they are far apart in Euclidean space. Another result is a technique for handling occlusion by incorporating the use of spatially local feature sets in the relaxation-type updating method.

Original languageEnglish (US)
Title of host publicationProceedings - International Conference on Pattern Recognition
PublisherIEEE
Pages195-197
Number of pages3
ISBN (Print)0818607424
StatePublished - Dec 1 1986

Publication series

NameProceedings - International Conference on Pattern Recognition

Fingerprint

Labeling
Semantics

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Henderson, T., & Samal, A. K. (1986). 2-D SCENE ANALYSIS USING SPLIT-LEVEL RELAXATION. In Proceedings - International Conference on Pattern Recognition (pp. 195-197). (Proceedings - International Conference on Pattern Recognition). IEEE.

2-D SCENE ANALYSIS USING SPLIT-LEVEL RELAXATION. / Henderson, Tom; Samal, Ashok K.

Proceedings - International Conference on Pattern Recognition. IEEE, 1986. p. 195-197 (Proceedings - International Conference on Pattern Recognition).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Henderson, T & Samal, AK 1986, 2-D SCENE ANALYSIS USING SPLIT-LEVEL RELAXATION. in Proceedings - International Conference on Pattern Recognition. Proceedings - International Conference on Pattern Recognition, IEEE, pp. 195-197.
Henderson T, Samal AK. 2-D SCENE ANALYSIS USING SPLIT-LEVEL RELAXATION. In Proceedings - International Conference on Pattern Recognition. IEEE. 1986. p. 195-197. (Proceedings - International Conference on Pattern Recognition).
Henderson, Tom ; Samal, Ashok K. / 2-D SCENE ANALYSIS USING SPLIT-LEVEL RELAXATION. Proceedings - International Conference on Pattern Recognition. IEEE, 1986. pp. 195-197 (Proceedings - International Conference on Pattern Recognition).
@inproceedings{cb5b5f760efc457fa9e22abcaa776c5d,
title = "2-D SCENE ANALYSIS USING SPLIT-LEVEL RELAXATION.",
abstract = "A new method is presented for applying multiple semantic constraints based on discrete relaxation. A separate graph is maintained for each constraint relation and is used in parallel to achieve a consistent labeling. This permits both local and global analysis without recourse to complete graphs. Here 'local' means with respect to particular constraint graph and thus actually includes global spatial relations on the features; e. g. , parallel edges on an object will be neighbors in the parallel constraint graph even though they are far apart in Euclidean space. Another result is a technique for handling occlusion by incorporating the use of spatially local feature sets in the relaxation-type updating method.",
author = "Tom Henderson and Samal, {Ashok K}",
year = "1986",
month = "12",
day = "1",
language = "English (US)",
isbn = "0818607424",
series = "Proceedings - International Conference on Pattern Recognition",
publisher = "IEEE",
pages = "195--197",
booktitle = "Proceedings - International Conference on Pattern Recognition",

}

TY - GEN

T1 - 2-D SCENE ANALYSIS USING SPLIT-LEVEL RELAXATION.

AU - Henderson, Tom

AU - Samal, Ashok K

PY - 1986/12/1

Y1 - 1986/12/1

N2 - A new method is presented for applying multiple semantic constraints based on discrete relaxation. A separate graph is maintained for each constraint relation and is used in parallel to achieve a consistent labeling. This permits both local and global analysis without recourse to complete graphs. Here 'local' means with respect to particular constraint graph and thus actually includes global spatial relations on the features; e. g. , parallel edges on an object will be neighbors in the parallel constraint graph even though they are far apart in Euclidean space. Another result is a technique for handling occlusion by incorporating the use of spatially local feature sets in the relaxation-type updating method.

AB - A new method is presented for applying multiple semantic constraints based on discrete relaxation. A separate graph is maintained for each constraint relation and is used in parallel to achieve a consistent labeling. This permits both local and global analysis without recourse to complete graphs. Here 'local' means with respect to particular constraint graph and thus actually includes global spatial relations on the features; e. g. , parallel edges on an object will be neighbors in the parallel constraint graph even though they are far apart in Euclidean space. Another result is a technique for handling occlusion by incorporating the use of spatially local feature sets in the relaxation-type updating method.

UR - http://www.scopus.com/inward/record.url?scp=0022955332&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0022955332&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0818607424

T3 - Proceedings - International Conference on Pattern Recognition

SP - 195

EP - 197

BT - Proceedings - International Conference on Pattern Recognition

PB - IEEE

ER -