Open AccessAutomatic image segmentation for concealed object detection using the expectation-maximization algorithm
Author(s) -
Dong Su Lee,
Seokwon Yeom,
JungYoung Son,
Shin-Hwan Kim
Publication year - 2010
Publication title -
optics express
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.394
H-Index - 271
ISSN - 1094-4087
DOI - 10.1364/oe.18.010659
Subject(s) - computer science , artificial intelligence , computer vision , expectation–maximization algorithm , segmentation , mixture model , image segmentation , object detection , image (mathematics) , object (grammar) , pattern recognition (psychology) , maximization , gaussian , maximum likelihood , mathematics , physics , mathematical optimization , statistics , quantum mechanics
We address an image segmentation method to detect concealed objects captured by passive millimeter wave (MMW) imaging. Passive MMW imaging can create interpretable imagery on the objects concealed under clothing, which gives the great advantage to the security system. In this paper, we propose the multi-level expectation maximization (EM) method to separate the concealed objects from the other area in the image. We apply the EM method to obtain a Gaussian mixture model (GMM) of the acquired image. In the experiments, we evaluate the performance by the average probability of error. We will show that the consecutive EM processes separates the object area more accurately than the conventional EM method.