The Consistent Labelling of Image Features using an ATMS | Zendy

R. Bodington | Zendy; G. D. Sullivan | Zendy; K. D. Baker | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

The Consistent Labelling of Image Features using an ATMS

Author(s) -

R. Bodington,

G. D. Sullivan,

K. D. Baker

Publication year - 1988

Publication title -

citeseer x (the pennsylvania state university)

Language(s) - English

Resource type - Conference proceedings

DOI - 10.5244/c.2.2

Subject(s) - labelling , image (mathematics) , constraint (computer aided design) , limiting , constraint satisfaction problem , limit (mathematics) , object (grammar) , computer science , artificial intelligence , constraint satisfaction , set (abstract data type) , computer vision , mathematics , engineering , programming language , mechanical engineering , mathematical analysis , geometry , criminology , sociology , probabilistic logic

Labelling sets of 2-D image features as model features is a constraint satisfaction problem that occurs in modelbased vision. The labelling must be consistent with constraints that describe how image features originating from the modelled object would appear in the image. This paper discusses how an assumption-ba sed truth maintenance system, ATMS, can be used to solve such a constraint satisfaction problem. The ATMS is used to limit the number of constraints applied, and to represent the multiple sets of consistent labels that are possible. The effectiveness of the ATMS in limiting the constraints is analysed.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research