Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
POP: Patchwork of Parts Models for Object Recognition
 

Summary: POP: Patchwork of Parts Models for Object
Recognition
Yali Amit
and Alain Trouv´e
January 15, 2007

Yali Amit is with the Department of Statistics and the department of Computer Science, University of
Chicago, Chicago, IL, 60637. Email: amit@marx.uchicago.edu. Supported in part by NSF ITR DMS-
0219016.

Alain Trouv´e is with the CMLA at the Ecole Normale Superieur, Cachan
1
Abstract
We formulate a deformable template model for objects with an efficient mecha-
nism for computation and parameter estimation. The data consists of binary oriented
edge features, robust to photometric variation and small local deformations. The tem-
plate is defined in terms of probability arrays for each edge type. A primary contri-
bution of this paper is the definition of the instantiation of an object in terms of shifts
of a moderate number local submodels - parts - which are subsequently recombined
using a patchwork operation, to define a coherent statistical model of the data. Ob-

  

Source: Amit, Yali - Departments of Computer Science & Statistics, University of Chicago

 

Collections: Computer Technologies and Information Sciences