Meaningful alignments

Agnès DESOLNEUX; Lionel MOISAN; Jean-Michel MOREL

doi:10.1023/A:1026593302236

Meaningful alignments

Agnès DESOLNEUX^*
, Lionel MOISAN
, Jean-Michel MOREL

^*Corresponding author for this work

Research output: Journal Publications › Journal Article (refereed) › peer-review

312 Citations (Scopus)

Abstract

We propose a method for detecting geometric structures in an image, without any a priori information. Roughly speaking, we say that an observed geometric event is 'meaningful' if the expectation of its occurrences would be very small in a random image. We discuss the apories of this definition, solve several of them by introducing 'maximal meaningful events' and analyzing their structure. This methodology is applied to the detection of alignments in images.

Original language	English
Pages (from-to)	7-23
Number of pages	17
Journal	International Journal of Computer Vision
Volume	40
Issue number	1
DOIs	https://doi.org/10.1023/A:1026593302236
Publication status	Published - Oct 2000
Externally published	Yes

Bibliographical note

We thank Jean Bretagnolle, Nicolas Vayatis, Frédéric Guichard and Isabelle Gaudron-Trouvé for valuable suggestions.

Funding

Work supported by Office of Naval Research under grant N00014-97-1-0839.

Access to Document

10.1023/A:1026593302236

Cite this

@article{c23a20c9401f4631ae7e67583e04cb35,

title = "Meaningful alignments",

abstract = "We propose a method for detecting geometric structures in an image, without any a priori information. Roughly speaking, we say that an observed geometric event is 'meaningful' if the expectation of its occurrences would be very small in a random image. We discuss the apories of this definition, solve several of them by introducing 'maximal meaningful events' and analyzing their structure. This methodology is applied to the detection of alignments in images.",

author = "Agn{\`e}s DESOLNEUX and Lionel MOISAN and Jean-Michel MOREL",

note = "We thank Jean Bretagnolle, Nicolas Vayatis, Fr{\'e}d{\'e}ric Guichard and Isabelle Gaudron-Trouv{\'e} for valuable suggestions.",

year = "2000",

month = oct,

doi = "10.1023/A:1026593302236",

language = "English",

volume = "40",

pages = "7--23",

journal = "International Journal of Computer Vision",

issn = "0920-5691",

publisher = "Springer Netherlands",

number = "1",

}

TY - JOUR

T1 - Meaningful alignments

AU - DESOLNEUX, Agnès

AU - MOISAN, Lionel

AU - MOREL, Jean-Michel

N1 - We thank Jean Bretagnolle, Nicolas Vayatis, Frédéric Guichard and Isabelle Gaudron-Trouvé for valuable suggestions.

PY - 2000/10

Y1 - 2000/10

N2 - We propose a method for detecting geometric structures in an image, without any a priori information. Roughly speaking, we say that an observed geometric event is 'meaningful' if the expectation of its occurrences would be very small in a random image. We discuss the apories of this definition, solve several of them by introducing 'maximal meaningful events' and analyzing their structure. This methodology is applied to the detection of alignments in images.

AB - We propose a method for detecting geometric structures in an image, without any a priori information. Roughly speaking, we say that an observed geometric event is 'meaningful' if the expectation of its occurrences would be very small in a random image. We discuss the apories of this definition, solve several of them by introducing 'maximal meaningful events' and analyzing their structure. This methodology is applied to the detection of alignments in images.

UR - https://www.scopus.com/pages/publications/0034291278

U2 - 10.1023/A:1026593302236

DO - 10.1023/A:1026593302236

M3 - Journal Article (refereed)

AN - SCOPUS:0034291278

SN - 0920-5691

VL - 40

SP - 7

EP - 23

JO - International Journal of Computer Vision

JF - International Journal of Computer Vision

IS - 1

ER -

Meaningful alignments

Abstract

Bibliographical note

Funding

Access to Document

Other files and links

Fingerprint

Cite this