January 1st, 2005 | RESEARCH
Multi-Touch technology provides a successful gesture based Human Computer Interface. The contact and gesture recognition algorithms of this interface are based on full hand function and, therefore, are not accessible to many people with physical disability. In this paper, we design a set of command-like gestures for users with limited range and function in their digits and wrist. Trajectory and angle features are extracted from these gestures and passed to a recurrent neural network for recognition. Experiments are performed to test the feasibility of gesture recognition system and determine the effect of network topology on the gesture recognition rate. These results show that the proposed method can successfully recognize those designed gestures for disabilities.
Document
(no document provided)
Team Members
Yu Yuan, Author, University of DelawareYing Liu, Author, University of Delaware
Kenneth Barner, Author, University of Delaware
Related URLs
Tags
Access and Inclusion: People with Disabilities
Audience: Evaluators | Museum | ISE Professionals | Scientists
Discipline: Computing and information science | Education and learning science
Resource Type: Reference Materials | Report
Environment Type: Media and Technology | Websites | Mobile Apps | Online Media