Computer vision for detecting and quantifying gamma-ray sources in coded-aperture images

Author

Schaich, Paul C. ; Clark, Gregory A. ; Sengupta, Sailes K. ; Ziock, Klaus-Peter

Author_Institution

Lawrence Livermore Nat. Lab., CA, USA

Volume

1

fYear

1994

fDate

31 Oct-2 Nov 1994

Firstpage

741

Abstract

We report the development of an automatic image analysis system that detects gamma-ray source regions in images obtained from a coded aperture, gamma-ray imager. The number of gamma sources in the image is plot known prior to analysis. The system counts the number (K) of gamma sources detected in the image and estimates the lower bound for the probability that the number of sources in the image is K. The system consists of a two-stage pattern classification scheme in which the probabilistic neural network is used in the supervised learning mode. The algorithms were developed and tested using real gamma-ray images from controlled experiments in which the number and location of depleted uranium source disks in the scene are known

Keywords

computer vision; gamma-rays; image classification; image coding; learning (artificial intelligence); neural nets; probability; signal detection; U; algorithms; automatic image analysis system; coded-aperture images; computer vision; controlled experiments; depleted uranium source disks; gamma-ray source regions; gamma-ray sources detection; lower bound; probabilistic neural network; probability; supervised learning mode; two-stage pattern classification; Apertures; Computer vision; Gamma ray detection; Gamma ray detectors; Image analysis; Layout; Neural networks; Pattern classification; Supervised learning; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Signals, Systems and Computers, 1994. 1994 Conference Record of the Twenty-Eighth Asilomar Conference on

Conference_Location

Pacific Grove, CA

ISSN

1058-6393

Print_ISBN

0-8186-6405-3

Type

conf

DOI

10.1109/ACSSC.1994.471550

Filename

471550