Contextual classification of cracks

N. Bryson; RN Dixon; JJ Hunter; CJ Taylor

Contextual classification of cracks

N. Bryson, RN Dixon, JJ Hunter, CJ Taylor

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

Abstract

We describe a technique for improving the classification of fragmented cues for cracks. Evidence propagation on Bayesian networks represents search within the context of each cue. The algorithm was applied to a data-set of cracks, and results demonstrate that contextual classification of the cues leads to significantly improved error rates. © 1994.

Original language	English
Pages (from-to)	149-154
Number of pages	5
Journal	Image and Vision Computing
Volume	12
Issue number	3
Publication status	Published - Apr 1994

Keywords

Bayesian networks
crack detection
machine vision

Cite this

@article{a1ad79c3e9de4da7a8e91c6e860324e2,

title = "Contextual classification of cracks",

abstract = "We describe a technique for improving the classification of fragmented cues for cracks. Evidence propagation on Bayesian networks represents search within the context of each cue. The algorithm was applied to a data-set of cracks, and results demonstrate that contextual classification of the cues leads to significantly improved error rates. {\textcopyright} 1994.",

keywords = "Bayesian networks, crack detection, machine vision",

author = "N. Bryson and RN Dixon and JJ Hunter and CJ Taylor",

year = "1994",

month = apr,

language = "English",

volume = "12",

pages = "149--154",

journal = "Image and Vision Computing",

issn = "0262-8856",

publisher = "Elsevier BV",

number = "3",

}

TY - JOUR

T1 - Contextual classification of cracks

AU - Bryson, N.

AU - Dixon, RN

AU - Hunter, JJ

AU - Taylor, CJ

PY - 1994/4

Y1 - 1994/4

N2 - We describe a technique for improving the classification of fragmented cues for cracks. Evidence propagation on Bayesian networks represents search within the context of each cue. The algorithm was applied to a data-set of cracks, and results demonstrate that contextual classification of the cues leads to significantly improved error rates. © 1994.

AB - We describe a technique for improving the classification of fragmented cues for cracks. Evidence propagation on Bayesian networks represents search within the context of each cue. The algorithm was applied to a data-set of cracks, and results demonstrate that contextual classification of the cues leads to significantly improved error rates. © 1994.

KW - Bayesian networks

KW - crack detection

KW - machine vision

M3 - Article

SN - 0262-8856

VL - 12

SP - 149

EP - 154

JO - Image and Vision Computing

JF - Image and Vision Computing

IS - 3

ER -

Contextual classification of cracks

Abstract

Keywords

Fingerprint

Cite this