Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

Adaptive Contextual Energy Parameterization for Automated Image Segmentation

Summary: Adaptive Contextual Energy Parameterization
for Automated Image Segmentation
Josna Rao1
, Ghassan Hamarneh2
, and Rafeef Abugharbieh1
Biomedical Signal and Image Computing Lab,
University of British Columbia, Canada
Medical Image Analysis Lab, Simon Fraser University, Canada
josnar@ece.ubc.ca, hamarneh@cs.sfu.ca, rafeef@ece.ubc.ca
Abstract. Image segmentation techniques are predominately based on
parameter-laden optimization processes. The segmentation objective func-
tion traditionally involves parameters (i.e. weights) that need to be tuned
in order to balance the underlying competing cost terms of image data fi-
delity and contour regularization. In this paper, we propose a novel ap-
proach for automatic adaptive energy parameterization. In particular, our
contributions are three-fold; 1) We spatially adapt fidelity and regulariza-
tion weights to local image content in an autonomous manner. 2) We mod-
ulate the weight using a novel contextual measure of image quality based


Source: Abugharbieh, Rafeef - Department of Electrical and Computer Engineering, University of British Columbia
Hamarneh, Ghassan - School of Computing Science, Simon Fraser University


Collections: Biology and Medicine; Computer Technologies and Information Sciences