| | |
Summary: Robust image recognition by fusion of contextual information
Xubo B. Song a,*, Yaser Abu-Mostafa b
, Joseph Sill c
, Harvey Kasdan d
, Misha Pavel a
a
Department of Electrical and Computer Engineering, OGI School of Science and Engineering, Oregon Health and Science University,
20000 NW Walker Road, Beaverton, OR 97006, USA
b
Learning Systems Group, Department of Electrical Engineering, California Institute of Technology, Pasadena, CA 91125, USA
c
Ripfire, 870 Market Street, Suite 1105, San Francisco, CA 94102, USA
d
International Remote Imaging Systems, Inc., 9162 Eton Avenue, Chatsworth, CA 91311, USA
Received 19 November 2001; received in revised form 13 May 2002; accepted 12 August 2002
Abstract
This paper studies the fusion of contextual information in pattern recognition, with applications to biomedical image identifi-
cation. In the real world there are cases where the identity of an object is ambiguous if the classification is based only on its own
features. It is helpful to reduce the ambiguity by utilizing extra information, referred to as context, provided by accompanying
objects. We investigate two techniques that incorporate context. The first approach, based on compound Bayesian theory, incor-
|
