Statistical Edge Detection of Concealed Weapons Using
Artificial Neural Networks

D 2008

Statistical Edge Detection of Concealed Weapons Using Artificial Neural Networks

WILLIAMS, Ian, David SVOBODA, Nicholas BOWRING a Elizabeth GUEST

Základní údaje

Originální název

Statistical Edge Detection of Concealed Weapons Using Artificial Neural Networks

Autoři

WILLIAMS, Ian (826 Velká Británie a Severní Irsko), David SVOBODA (203 Česká republika, garant, domácí), Nicholas BOWRING (826 Velká Británie a Severní Irsko) a Elizabeth GUEST (826 Velká Británie a Severní Irsko)

Vydání

Vol. 6812. Bellingham, Washington, Proceedings of SPIE-IS&T Electronic Imaging, od s. 68121J-1-12, 12 s. 2008

Nakladatel

SPIE

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

20200 2.2 Electrical engineering, Electronic engineering, Information engineering

Stát vydavatele

Spojené státy

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL

Kód RIV

RIV/00216224:14330/08:00042085

Organizační jednotka

Fakulta informatiky

ISBN

978-0-8194-6984-7

ISSN

UT WoS

000256350500050

Klíčová slova anglicky

statistical edge detection; neural networks; image processing

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 11. 4. 2012 10:00, doc. RNDr. David Svoboda, Ph.D.

Anotace

V originále

A novel edge detector has been developed that utilizes statistical masks and neural networks for the optimal detection of edges over a wide range of image types. The failure of many common edge detection techniques has been observed when analyzing concealed weapons X-ray images, biomedical images or images with significant levels of noise, clutter or texture. This novel technique is based on a statistical edge detection filter that uses a range of two-sample statistical tests to evaluate any local image texture differences. The range and type of tests has been greatly expanded from the previous works. This process is further enhanced by applying combined multiple scale pixel masks and multiple statistical tests, to Artificial Neural Networks (ANN) trained to classify different edge types. Through the use of Artificial Neural Networks (ANN) we can combine the output results of several statistical mask scales into one detector. Furthermore we can allow the combination of several two sample statistical tests of varying properties (for example; mean based, variance based and distribution based). This combination of both scales and tests allows the optimal response from a variety of statistical masks. From this we can produce the optimum edge detection output for a wide variety of images, and the results of this are presented.

Návaznosti

1K05021, projekt VaV

Název: Rekonstrukce objektů v biomedicínských obrazech pomocí statistických metod a metod umělé inteligence

Investor: Ministerstvo školství, mládeže a tělovýchovy ČR, Rekonstrukce objektů v biomedicínských obrazech pomocí statistických metod a metod umělé inteligence

Citovat

WILLIAMS, Ian, David SVOBODA, Nicholas BOWRING a Elizabeth GUEST. Statistical Edge Detection of Concealed Weapons Using Artificial Neural Networks. In Proceedings of SPIE-IS&T Electronic Imaging. Vol. 6812. Bellingham, Washington: SPIE, 2008, s. 68121J-1-12, 12 s. ISBN 978-0-8194-6984-7.

@inproceedings{785293,
   author = {Williams, Ian and Svoboda, David and Bowring, Nicholas and Guest, Elizabeth},
   address = {Bellingham, Washington},
   booktitle = {Proceedings of SPIE-IS&T Electronic Imaging},
   edition = {Vol. 6812},
   keywords = {statistical edge detection; neural networks; image processing},
   language = {eng},
   location = {Bellingham, Washington},
   isbn = {978-0-8194-6984-7},
   pages = {68121J-1-12},
   publisher = {SPIE},
   title = {Statistical Edge Detection of Concealed Weapons Using Artificial Neural Networks},
   url = {http://dx.doi.org/10.1117/12.766472},
   year = {2008}
}

TY  - JOUR
ID  - 785293
AU  - Williams, Ian - Svoboda, David - Bowring, Nicholas - Guest, Elizabeth
PY  - 2008
TI  - Statistical Edge Detection of Concealed Weapons Using Artificial Neural Networks
PB  - SPIE
CY  - Bellingham, Washington
SN  - 9780819469847
KW  - statistical edge detection
KW  - neural networks
KW  - image processing
UR  - http://dx.doi.org/10.1117/12.766472
N2  - A novel edge detector has been developed that utilizes statistical masks and neural networks for the optimal detection of edges over a wide range of image types. The failure of many common edge detection techniques has been observed when analyzing concealed weapons X-ray images, biomedical images or images with significant levels of noise, clutter or texture. This novel technique is based on a statistical edge detection filter that uses a range of two-sample statistical tests to evaluate any local image texture differences. The range and type of tests has been greatly expanded from the previous works. This process is further enhanced by applying combined multiple scale pixel masks and multiple statistical tests, to Artificial Neural Networks (ANN) trained to classify different edge types. Through the use of Artificial Neural Networks (ANN) we can combine the output results of several statistical mask scales into one detector. Furthermore we can allow the combination of several two sample statistical tests of varying properties (for example; mean based, variance based and distribution based). This combination of both scales and tests allows the optimal response from a variety of statistical masks. From this we can produce the optimum edge detection output for a wide variety of images, and the results of this are presented.
ER  -

WILLIAMS, Ian, David SVOBODA, Nicholas BOWRING a Elizabeth GUEST. Statistical Edge Detection of Concealed Weapons Using Artificial Neural Networks. In \textit{Proceedings of SPIE-IS\&{}T Electronic Imaging}. Vol. 6812. Bellingham, Washington: SPIE, 2008, s.~68121J-1-12, 12 s. ISBN~978-0-8194-6984-7.

Podrobný výpis o publikaci