AUTOMATIC IMAGE-ANALYSIS FOR DETECTING AND QUANTIFYING GAMMA-RAY SOURCES IN CODED-APERTURE IMAGES

We report the development of an automatic image analysis system that d etects gamma-ray source regions in images obtained from a coded apertu re, gamma-ray imager. The number of gamma sources in the image Is not known prior to analysis, The system counts the number (Ii) of gamma so urces detected in the image and estimates the lower bound for the prob ability that the number of sources in the image is K. The system consi sts of a two-stage pattern classification scheme in which the probabil istic neural network is used in the supervised learning mode, The algo rithms were developed and tested using real gamma-ray images from cont rolled experiments in which the number and location of depleted uraniu m source disks in the scene are known, The novelty of the work lies in the creative combination of algorithms and the successful application of the algorithms to real images of gamma-ray sources.