On deformable models for visual pattern recognition

Kwok Wai CHEUNG*, Dit Yan Yeung, Roland T. CHIN

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

31 Citations (Scopus)


This paper reviews model-based methods for non-rigid shape recognition. These methods model, match and classify non-rigid shapes, which are generally problematic for conventional algorithms using rigid models. Issues including model representation, optimization criteria formulation, model matching, and classification are examined in detail with the objective to provide interested researchers a roadmap for exploring the field. This paper emphasizes on 2D deformable models. Their potential applications and future research directions, particularly on deformable pattern classification, are discussed.

Original languageEnglish
Pages (from-to)1507-1526
Number of pages20
JournalPattern Recognition
Issue number7
Early online date19 Mar 2002
Publication statusPublished - Jul 2002

Scopus Subject Areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

User-Defined Keywords

  • Classification
  • Constraint incorporation
  • Criteria formulation
  • Deformable models
  • Initialization
  • Matching
  • Model representation
  • Optimization
  • Regularization
  • Topology adaptation


Dive into the research topics of 'On deformable models for visual pattern recognition'. Together they form a unique fingerprint.

Cite this