Summary: Personal and Ubiquitous Computing manuscript No.
(will be inserted by the editor)
A Database­Based Framework for Gesture Recognition
Vassilis Athitsos · Haijing Wang · Alexandra Stefan
Received: date / Accepted: date
Abstract Gestures are an important modality for human­machine communication. Com­
puter vision modules performing gesture recognition can be important components of in­
telligent homes, assistive environments, and human­computer interfaces. A key problem
in recognizing gestures is that the appearance of a gesture can vary widely depending on
variables such as the person performing the gesture, or the position and orientation of the
camera. This paper presents a database­based approach for addressing this problem. The
large variability in appearance among different examples of the same gesture is addressed
by creating large gesture databases, that store enough exemplars from each gesture to capture
the variability within that gesture. This database­based approach is applied to two gesture
recognition problems: handshape categorization and motion­based recognition of American
Sign Language (ASL) signs. A key aspect of our approach is the use of database indexing
methods, in order to address the challenge of searching large databases without violating the
time constraints of an online interactive system, where system response times of over a few
seconds are oftentimes considered unacceptable. Our experiments demonstrate the benefits
of the proposed database­based framework, and the feasibility of integrating large gesture

Source: Athitsos, Vassilis - Department of Computer Science and Engineering, University of Texas at Arlington

Collections: Computer Technologies and Information Sciences