Presentation	2012-01-19 Robust Non-rigid Cluster-Based Registration with Confidence Self-Evaluation Yoshihide SAWADA, Hidekata HONTANI,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	In this article, we propose a robust non-rigid surface registration method, which registers a surface model to given images and which evaluates the confidence of the registration. A target surface is divided into local clusters, and the statistics of their shapes are parametrically represented in the surface model. The method registers the model by estimating the values of the parameters. Assuming that the sparseness of outliers in a given image, the proposed method automatically detects the outliers and ignores them to robustly register the model. For this robust registration, we employ the L1-norm regularization. Experimemtal results on the liver registration demonstrate the performance of the proposed method.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Non-rigid registration / Confidence evaluation / Outlier detection
Paper #	MI2011-77
Date of Issue

Conference Information
Committee	MI
Conference Date	2012/1/12(1days)
Place (in Japanese)	(See Japanese page)
Place (in English)
Topics (in Japanese)	(See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To	Medical Imaging (MI)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	Robust Non-rigid Cluster-Based Registration with Confidence Self-Evaluation
Sub Title (in English)
Keyword(1)	Non-rigid registration
Keyword(2)	Confidence evaluation
Keyword(3)	Outlier detection
1st Author's Name	Yoshihide SAWADA
1st Author's Affiliation	Nagoya Insutitute of Technology()
2nd Author's Name	Hidekata HONTANI
2nd Author's Affiliation	Nagoya Insutitute of Technology
Date	2012-01-19
Paper #	MI2011-77
Volume (vol)	vol.111
Number (no)	389
Page	pp.pp.-
#Pages	6
Date of Issue