Model-Based Matching of Line Drawings by Linear Combinations of Prototypes


Autoria(s): Jones, Michael J.; Poggio, Tomaso
Data(s)

20/10/2004

20/10/2004

18/01/1996

Resumo

We describe a technique for finding pixelwise correspondences between two images by using models of objects of the same class to guide the search. The object models are 'learned' from example images (also called prototypes) of an object class. The models consist of a linear combination ofsprototypes. The flow fields giving pixelwise correspondences between a base prototype and each of the other prototypes must be given. A novel image of an object of the same class is matched to a model by minimizing an error between the novel image and the current guess for the closest modelsimage. Currently, the algorithm applies to line drawings of objects. An extension to real grey level images is discussed.

Formato

7 p.

442803 bytes

265964 bytes

application/postscript

application/pdf

Identificador

AIM-1559

CBCL-128

http://hdl.handle.net/1721.1/7187

Idioma(s)

en_US

Relação

AIM-1559

CBCL-128

Palavras-Chave #AI #MIT #Artificial Intelligence #computer vision #scorrespondence #model-based matching