Host: The Japan Society of Mechanical Engineers
Name : [in Japanese]
Date : June 08, 2016 - June 11, 2016
Recently, robotic cooking support systems that help human's cooking operations have been developed. However, since these systems usually need many sensors to recognize human's cooking operations, it is difficult to introduce these system in a ordinary kitchen. In this study, we use CHLAC(Cubic Higher-order Local Auto-Collelation) features to recognize human's cooking operations. Further, Fisher linear discriminant is used to map the CHLAC feature space into the low dimension space, and the results verified the validity of the proposed approach.
