TY - GEN
T1 - Grasp recognition with uncalibrated data gloves - A comparison of classification methods
AU - Heumer, Guido
AU - Amor, Heni Ben
AU - Weber, Matthias
AU - Jung, Bernhard
N1 - Copyright:
Copyright 2008 Elsevier B.V., All rights reserved.
PY - 2007
Y1 - 2007
N2 - This paper presents a comparison of various classification methods for the problem of recognizing grasp types involved in object manipulations performed with a data glove. Conventional wisdom holds that data gloves need calibration in order to obtain accurate results. However, calibration is a time-consuming process, inherently user-specific, and its results are often not perfect. In contrast, the present study aims at evaluating recognition methods that do not require prior calibration of the data glove, by using raw sensor readings as input features and mapping them directly to different categories of hand shapes. An experiment was carried out, where test persons wearing a data glove had to grasp physical objects of different shapes corresponding to the various grasp types of the Schlesinger taxonomy. The collected data was analyzed with 28 classifiers including different types of neural networks, decision trees, Bayes nets, and lazy learners. Each classifier was analyzed in six different settings, representing various application scenarios with differing generalization demands. The results of this work are twofold: (1) We show that a reasonably well to highly reliable recognition of grasp types can be achieved - depending on whether or not the glove user is among those training the classifier - even with uncalibrated data gloves. (2) We identify the best performing classification methods for recognition of various grasp types. To conclude, cumbersome calibration processes before productive usage of data gloves can be spared in many situations.
AB - This paper presents a comparison of various classification methods for the problem of recognizing grasp types involved in object manipulations performed with a data glove. Conventional wisdom holds that data gloves need calibration in order to obtain accurate results. However, calibration is a time-consuming process, inherently user-specific, and its results are often not perfect. In contrast, the present study aims at evaluating recognition methods that do not require prior calibration of the data glove, by using raw sensor readings as input features and mapping them directly to different categories of hand shapes. An experiment was carried out, where test persons wearing a data glove had to grasp physical objects of different shapes corresponding to the various grasp types of the Schlesinger taxonomy. The collected data was analyzed with 28 classifiers including different types of neural networks, decision trees, Bayes nets, and lazy learners. Each classifier was analyzed in six different settings, representing various application scenarios with differing generalization demands. The results of this work are twofold: (1) We show that a reasonably well to highly reliable recognition of grasp types can be achieved - depending on whether or not the glove user is among those training the classifier - even with uncalibrated data gloves. (2) We identify the best performing classification methods for recognition of various grasp types. To conclude, cumbersome calibration processes before productive usage of data gloves can be spared in many situations.
KW - Calibration
KW - Classification methods
KW - Data glove
KW - Grasp recognition
UR - http://www.scopus.com/inward/record.url?scp=34547650835&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=34547650835&partnerID=8YFLogxK
U2 - 10.1109/VR.2007.352459
DO - 10.1109/VR.2007.352459
M3 - Conference contribution
AN - SCOPUS:34547650835
SN - 1424409055
SN - 9781424409051
T3 - Proceedings - IEEE Virtual Reality
SP - 19
EP - 26
BT - IEEE Virtual Reality 2007, VR'07, Proceedings
T2 - 2007 IEEE Virtual Reality Conference, VR'07
Y2 - 10 March 2007 through 14 March 2007
ER -