THIS PAGE INCORPORATES CASCADING STYLE SHEET! TO VIEW PAGE CORRECTLY PLEASE UPDATE TO A CSS COMPLIANT BROWSER
A Class of Stochastic Models for Invariant Recognition
UR > CS > Research > Vision > Publications > A Class of Stochastic Models for Invariant Recognition
pdf 189 KB
ps.gz 341 KB
ps 1.20 MB
@TechReport{Rao:TR96b,
  author = 	 {Rajesh P.N. Rao and Dana H. Ballard},
  title = 	 {A Class of Stochastic Models for Invariant Recognition},
  institution =  {Computer Science Department University of Rochester},
  year = 	 {1996},
  number = 	 {96.1},
  address = 	 {Rochester NY},
  month = 	 {June},
  abstract =  {  We describe a general framework for modeling transformations in the image plane
using a stochastic generative model. Algorithms that resemble the well­known
Kalman filter are derived from the MDL principle for estimating both the generative
weights and the current transformation state. The generative model is assumed
to be implemented in cortical feedback pathways while the feedforward pathways
implement an approximate inverse model to facilitate the estimation of current state.
Using the above framework, we derive models for invariant recognition, motion
estimation, and stereopsis, and present preliminary simulation results demonstrating
recognition of objects in the presence of translations, rotations and scale changes.  }
}