AI-EigenSnake: An affine-invariant deformable contour model for object matching

Zhong Xue, Stan Z. Li, Eam Khwang Teoh

Research output: Contribution to journalArticle

24 Scopus citations

Abstract

An affine-invariant (AI) deformable contour model for object matching, called AI-EigenSnake (AI-ES), is proposed in the Bayesian framework. In AI-ES, the prior distribution of object shapes is estimated from the sample data. This distribution is then used to constrain the prototype contour, which is dynamically adjustable in the matching process. In this way, large shape deformations due to the variations of samples can be tolerated. Moreover, an AI internal energy term is introduced to describe the shape deformations between the prototype contour in the shape domain and the deformable contour in the image domain. Experiments based on real object matching demonstrate that the proposed model is more robust and insensitive to the positions, viewpoints, and large deformations of object shapes, as compared to the Active Shape Model and the AI-Snake Model.

Original languageEnglish (US)
Pages (from-to)77-84
Number of pages8
JournalImage and Vision Computing
Volume20
Issue number2
DOIs
StatePublished - Feb 1 2002

Keywords

  • Active shape model
  • Affine invariant
  • Deformable model
  • EigenSnake
  • Object matching

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'AI-EigenSnake: An affine-invariant deformable contour model for object matching'. Together they form a unique fingerprint.

Cite this