Joint detection, segmentation, and registration of elastically deformable objects

Gilad Cohen, Joseph M. Francos, Rami Hagege

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We present a new approach to the general problem of template-based detection, segmentation, and registration of elastically deformable objects. This joint problem is highly nonlinear and high dimensional, due to the large space of possible geometric transformations between a given template and its observed signature. Hence, any attempt to directly solve it inevitably leads to a high dimensional, nonlinear, nonconvex optimization procedure. We propose a novel parametric solution to this problem, by showing that it can be equivalently represented by a low dimensional model, which is linear in the deformation parameters, and biased by the unknown observation background. Linear Bayesian estimation is then employed to estimate the deformation parameters, and a likelihood ratio test is utilized to detect a deformed instance of the template, thus providing an explicit closed-form solution for the joint problem.

Original languageEnglish
Title of host publication2008 42nd Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2008
Pages1209-1213
Number of pages5
DOIs
StatePublished - 1 Dec 2008
Event2008 42nd Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2008 - Pacific Grove, CA, United States
Duration: 26 Oct 200829 Oct 2008

Publication series

NameConference Record - Asilomar Conference on Signals, Systems and Computers
ISSN (Print)1058-6393

Conference

Conference2008 42nd Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2008
Country/TerritoryUnited States
CityPacific Grove, CA
Period26/10/0829/10/08

Cite this