Aligning shapes by minimising the description length

Anders Ericsson, Johan Karlsson

Research output: Contribution to journalArticlepeer-review

4 Citations (SciVal)

Abstract

When building shape models, it is first necessary to filter out the similarity transformations from the original configurations. This is normally done using Procrustes analysis, that is minimising the sum of squared distances between the corresponding landmarks under similarity transformations. In this article we propose to align shapes using the Minimum Description Length (MDL) criterion. Previously MDL has been used to locate correspondences. We show that the Procrustes alignment with respect to rotation is not optimal. The MDL based algorithm is compared with Procrustes on a number of data sets. It is concluded that there is improvement in generalisation when using Minimum Description Length. With a synthetic example it is shown that the Procrustes alignment can fail significantly where the proposed method does not. The Description Length is minimised using Gauss-Newton. In order to do this the derivative of the description length with respect to rotation is derived.
Original languageEnglish
Pages (from-to)709-718
JournalLecture Notes in Computer Science
Volume3540
DOIs
Publication statusPublished - 2005

Subject classification (UKÄ)

  • Mathematics

Fingerprint

Dive into the research topics of 'Aligning shapes by minimising the description length'. Together they form a unique fingerprint.

Cite this