Generative models and Bayesian model comparison for shape recognition

Balaji Krishnapuram, C.M. Bishop, M. Szummer

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Recognition of hand-drawn shapes is an important and widely studied problem. By adopting a generative probabilistic framework we are able to formulate a robust and flexible approach to shape recognition which allows for a wide range of shapes and which can recognize new shapes from a single exemplar. It also provides meaningful probabilistic measures of model score, which can be used as part of a larger probabilistic framework for interpreting a page of ink. We also show how Bayesian model comparison allows the trade-off between data fit and model complexity to be optimized automatically.
Original languageEnglish
Title of host publicationFrontiers in Handwriting Recognition, 2004. IWFHR-9 2004. Ninth International Workshop on
Number of pages6
Publication statusPublished - 1 Oct 2004

Keywords / Materials (for Non-textual outputs)

  • Bayes methods
  • handwritten character recognition
  • object recognition
  • temporal databases
  • Bayesian model
  • generative model
  • generative probabilistic framework
  • hand drawn shape recognition
  • temporal information
  • Bayesian methods
  • Conferences
  • Fitting
  • Handwriting recognition
  • Ink
  • Robustness
  • Shape
  • USA Councils


Dive into the research topics of 'Generative models and Bayesian model comparison for shape recognition'. Together they form a unique fingerprint.

Cite this