Paper Info
Title
Pointing gesture recognition using compressed sensing for training data reduction
Abstract
In this paper, we investigate training data reduction for the pointing gesture recognition with compressed sensing. The pointing gesture is one of activities during pointing and calling that is carried out by workers to keep occupational safety and correctness. Compressed sensing is used for gesture recognition and considered the impacts of the gesture duration difference among user. However, the different force among users may affect to the recognition. As a result of the experiment, F-measure is improved 0.18 compared with the DTW even only the data obtained from others is used. Moreover, we found that the user-dependency varies for each subject. Therefore, we tested to recognize the pointing gestures of all subjects by using the training data of only specific users. The test showed that the recognition model with training data from 4 specific subjects provided the same accuracy as the one from 11 subjects. This result suggested the feasibility of reduction for subjects who need to acquire the training data.
Year
DOI
Venue
2013
10.1145/2494091.2495985
UbiComp (Adjunct Publication)
Keywords
DocType
Citations 
gesture duration difference,specific subject,recognition model,occupational safety,training data reduction,different force,gesture recognition,specific user,training data,ubiquitous computing
Conference
0
PageRank 
References 
Authors
0.34
10
2
Name
Order
Citations
PageRank
Masahiro Iwasaki100.34
Kaori Fujinami231641.25