| | |
Summary: Nearest Neighbor Search Methods for Handshape
Recognition
Michalis Potamias1
and Vassilis Athitsos2
1
Computer Science Department, Boston University
2
Computer Science and Engineering Department, University of Texas at Arlington
ABSTRACT
Gestures are an important modality for human-machine communi-
cation, and robust gesture recognition can be an important com-
ponent of intelligent homes and assistive environments in general.
An important aspect of gestures is handshape. Handshapes can
hold important information about the meaning of a gesture, for ex-
ample in sign languages, or about the intent of an action, for ex-
ample in manipulative gestures or in virtual reality interfaces. At
the same time, recognizing handshape can be a very challenging
task, because the same handshape can look very different in dif-
ferent images, depending on the 3D orientation of the hand and
the viewpoint of the camera. In this paper we examine a database
|
