One of the central problems in stereo matching (and other image registration tasks) is the selection of optimal window sizes for comparing image regions. This paper addresses this ...
We revisit the problem of model-based object recognition for intensity images and attempt to address some of the shortcomings of existing Bayesian methods, such as unsuitable prior...
We present a template-based approach to detecting human silhouettes in a specific walking pose. Our templates consist of short sequences of 2D silhouettes obtained from motion cap...
Abstract- This paper describes the generation and utilisation of a pattern database for 19x19 go with the Knearest-neighbor representation. Patterns are generated by browsing recor...
This paper proposes a method for Bayesian networks that handles uncertainty and discretization of continuous variables when learning the networks from a database of cases. The dat...