SICE Journal of Control, Measurement, and System Integration
Online ISSN : 1884-9970
Print ISSN : 1882-4889
INVITED PAPERS
An Information Theoretic Approach for Active and Effective Object Recognitions
Koichiro DEGUCHI
Author information
JOURNALS FREE ACCESS

2008 Volume 1 Issue 1 Pages 33-39

Details
Abstract

This paper describes a strategy of optimal sensing action selection for recognition of the observed object among those registered in the image data base. This strategy is built from an information theoretic point of view. The goal is to reduce the number and effort of the recognition steps to reach the final decision of the recognition. We have chosen an information theoretic framework, motivated by the fact that sensored image data is not noiseless or ideal, nor can the effect of a certain action be completely determined in advance. We present an actual strategy of the recognition process, and then, the results of the feasibility study by experiments.

Information related to the author
© 2008 The Society of Instrument and Control Engineers
Previous article Next article
feedback
Top