Learning to describe and efficiently recognize patterns and objects in scenes

Author

Caelli, Terry ; Bischof, Walter F.

Author_Institution

Dept. of Comput. Sci., Curtin Univ. of Technol., Perth, WA, Australia

Volume

4

fYear

1996

fDate

14-17 Oct 1996

Firstpage

2756

Abstract

Machine learning has been applied to many problems related to scene interpretation. It has become clear from these studies that it is important to develop or choose learning procedures appropriate for the types of data models involved in a given problem formulation. We focus on this issue of learning with respect to different data structures and consider, in particular, problems related to the learning of relational structures in visual data. Finally, we discuss problems related to rule evaluation in multi-object complex scenes and introduce some new techniques to solve them

Keywords

data structures; decision theory; learning (artificial intelligence); object recognition; pattern classification; probability; trees (mathematics); data models; data structures; machine learning; multi-object complex scenes; relational structures; rule evaluation; Computer science; Data structures; Layout; Machine learning; Object detection; Object recognition; Pattern matching; Pattern recognition; Psychology; Robustness;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man, and Cybernetics, 1996., IEEE International Conference on

Conference_Location

Beijing

ISSN

1062-922X

Print_ISBN

0-7803-3280-6

Type

conf

DOI

10.1109/ICSMC.1996.561376

Filename

561376