Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

A Neural Network Architecture for Visual Selection

Summary: A Neural Network Architecture for
Visual Selection
Yali Amit
May 25, 2006
This paper describes a parallel neural net architecture for efficient and
robust visual selection in generic gray level images. Objects are repre-
sented through flexible star type planar arrangements of binary local fea-
tures, which are in turn star type planar arrangements of oriented edges.
Candidate locations are detected over a range of scales and other defor-
mations, using a generalized Hough transform. The flexibility of the ar-
rangements provides the required invariance. Training involves selecting a
small number of stable local features, from a predefined pool, which are well
localized on registered examples of the object. Training therefore requires
only small data sets. The parallel architecture is constructed so that the
Hough transform associated with any object can be implemented without
creating or modifying any connections. The different object representations
are learned and stored in a central module. When one of these represen-
tations is evoked, it `primes' the appropriate layers in the network so that
the corresponding Hough transform is computed. Analogies between the


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


Collections: Computer Technologies and Information Sciences