An affine-invariant active contour model (AI-snake) for model-based segmentation

Horace H.S. Ip, Dinggang Shen

Research output: Contribution to journalArticlepeer-review

69 Citations (Scopus)


In this paper, we show that existing shaped-based active contour models are not affine-invariant and we addressed the problem by presenting an affine-invariant snake model (AI-snake) such that its energy function are defined in terms local and global affine-invariant features. The main characteristic of the AI-snake is that, during the process of object extraction, the pose of the model contour is dynamically adjusted such that it is in alignment with the current snake contour by solving the snake-prototype correspondence problem and determining the required affine transformation. In addition, we formulate the correspondence matching between the snake and the object prototype as an error minimization process between two feature vectors which capture both local and global deformation information. We show that the technique is robust against object deformations and complex scenes.

Original languageEnglish
Pages (from-to)135-146
Number of pages12
JournalImage and Vision Computing
Issue number2
Publication statusPublished - 1998 Feb 20


  • Active contour
  • Affine invariant
  • Correspondence matching
  • Curvature
  • Deformable model
  • Model-based
  • Object tracking
  • Snake

ASJC Scopus subject areas

  • Signal Processing
  • Computer Vision and Pattern Recognition

Cite this