Generative model based vision

✍ Scribed by Arthur E.C Pece

• Publisher: Elsevier Science
• Year: 2003
• Tongue: English
• Weight: 64 KB
• Volume: 21
• Category: Article
• ISSN: 0262-8856
• DOI: 10.1016/s0262-8856(02)00124-5

✦ Synopsis

During the last decade, there has been a convergence of statistical and model-based approaches to computational vision. This is an ongoing process, leading to the emerging paradigm of generative-model-based (GMB) vision. This special issue of Image and Vision Computing contains revised versions of 12 papers presented at the first international workshop on Generative-Model-Based Vision. The workshop was held in Copenhagen on the 2nd of June 2002, with the purpose of bringing together researchers working on different problems within computational vision, who are interested in the GMB approach.

For the purposes of the workshop, GMB vision was defined as a methodology which prescribes † the formulation of a parameterized probabilistic model of image generation; † estimation and/or maximization of the posterior probability of model parameters, given an image or image sequence.

This definition was not meant to be dogmatic or to inhibit the development of the field, but only to give a focus to the presentations.