Statistical Fourier Descriptors for Defect Image Classification

Fabian Timm; Thomas Martinetz

doi:10.1109/ICPR.2010.1018

Statistical Fourier Descriptors for Defect Image Classification

Institut für Neuro- und Bioinformatik

Abstract

In many industrial applications, Fourier descriptors are commonly used when the description of the object shape is an important characteristic of the image. However, these descriptors are limited to single objects. We propose a general Fourier-based approach, called statistical Fourier descriptor (SFD), which computes shape statistics in grey level images. The SFD is computationally efficient and can be used for defect image classification. In a first example, we deployed the SFD to the inspection of welding seams with promising results.

Originalsprache	Englisch
Titel	Proceedings of the 20th Int. Conference on Pattern Recognition (ICPR)
Seitenumfang	4
Herausgeber (Verlag)	IEEE
Erscheinungsdatum	07.10.2010
Seiten	4190-4193
ISBN (Print)	978-1-4244-7542-1
ISBN (elektronisch)	978-1-4244-7541-4
DOIs	https://doi.org/10.1109/ICPR.2010.1018
Publikationsstatus	Veröffentlicht - 07.10.2010
Veranstaltung	2010 20th International Conference on Pattern Recognition - Istanbul, Türkei Dauer: 23.08.2010 → 26.08.2010

UN SDGs

Dieser Output leistet einen Beitrag zu folgendem(n) Ziel(en) für nachhaltige Entwicklung

Dokumente

10.1109/ICPR.2010.1018

TiMa10Endgültige, publizierte Fassung (Verlagsversion), 522 KB

Zitieren

@inproceedings{0663e64ba57b4ab589224786cdb289a2,

title = "Statistical Fourier Descriptors for Defect Image Classification",

abstract = "In many industrial applications, Fourier descriptors are commonly used when the description of the object shape is an important characteristic of the image. However, these descriptors are limited to single objects. We propose a general Fourier-based approach, called statistical Fourier descriptor (SFD), which computes shape statistics in grey level images. The SFD is computationally efficient and can be used for defect image classification. In a first example, we deployed the SFD to the inspection of welding seams with promising results.",

author = "Fabian Timm and Thomas Martinetz",

year = "2010",

month = oct,

day = "7",

doi = "10.1109/ICPR.2010.1018",

language = "English",

isbn = "978-1-4244-7542-1",

series = "Proceedings of the IEEE",

publisher = "IEEE",

pages = "4190--4193",

booktitle = "Proceedings of the 20th Int. Conference on Pattern Recognition (ICPR)",

note = "2010 20th International Conference on Pattern Recognition ; Conference date: 23-08-2010 Through 26-08-2010",

}

TY - GEN

T1 - Statistical Fourier Descriptors for Defect Image Classification

AU - Timm, Fabian

AU - Martinetz, Thomas

PY - 2010/10/7

Y1 - 2010/10/7

N2 - In many industrial applications, Fourier descriptors are commonly used when the description of the object shape is an important characteristic of the image. However, these descriptors are limited to single objects. We propose a general Fourier-based approach, called statistical Fourier descriptor (SFD), which computes shape statistics in grey level images. The SFD is computationally efficient and can be used for defect image classification. In a first example, we deployed the SFD to the inspection of welding seams with promising results.

AB - In many industrial applications, Fourier descriptors are commonly used when the description of the object shape is an important characteristic of the image. However, these descriptors are limited to single objects. We propose a general Fourier-based approach, called statistical Fourier descriptor (SFD), which computes shape statistics in grey level images. The SFD is computationally efficient and can be used for defect image classification. In a first example, we deployed the SFD to the inspection of welding seams with promising results.

U2 - 10.1109/ICPR.2010.1018

DO - 10.1109/ICPR.2010.1018

M3 - Conference contribution

SN - 978-1-4244-7542-1

T3 - Proceedings of the IEEE

SP - 4190

EP - 4193

BT - Proceedings of the 20th Int. Conference on Pattern Recognition (ICPR)

PB - IEEE

T2 - 2010 20th International Conference on Pattern Recognition

Y2 - 23 August 2010 through 26 August 2010

ER -

Statistical Fourier Descriptors for Defect Image Classification

Abstract

UN SDGs

Dokumente

Fingerprint

Zitieren