TY - GEN
T1 - An information theoretic approach for active and effective object recognitions
AU - Deguchi, Koichiro
AU - Ohtsu, Hiromi
PY - 2006
Y1 - 2006
N2 - This paper describes the strategy of optimal action selection for recognition of the observed object among those registered in the image data base 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 the strategy of the recognition process, and then, the results of the feasibility study by experiments.
AB - This paper describes the strategy of optimal action selection for recognition of the observed object among those registered in the image data base 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 the strategy of the recognition process, and then, the results of the feasibility study by experiments.
UR - http://www.scopus.com/inward/record.url?scp=34047233876&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=34047233876&partnerID=8YFLogxK
U2 - 10.1109/ICPR.2006.252
DO - 10.1109/ICPR.2006.252
M3 - Conference contribution
AN - SCOPUS:34047233876
SN - 0769525210
SN - 9780769525211
T3 - Proceedings - International Conference on Pattern Recognition
SP - 622
EP - 625
BT - Proceedings - 18th International Conference on Pattern Recognition, ICPR 2006
T2 - 18th International Conference on Pattern Recognition, ICPR 2006
Y2 - 20 August 2006 through 24 August 2006
ER -