Visual Interpretation of Hand Gestures for Human-Computer Interaction: A Review
IEEE Transactions on Pattern Analysis and Machine Intelligence
Real-Time American Sign Language Recognition Using Desk and Wearable Computer Based Video
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Real-Time Continuous Gesture Recognition System for Sign Language
FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
Finding Pose of Hand in Video Images: A Stereo-Based Approach
FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
Gesture Modeling and Recognition Using Finite State Machines
FG '00 Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition 2000
An Appearance-Based Framework for 3D Hand Shape Classification and Camera Viewpoint Estimation
FGR '02 Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition
Parametric correspondence and chamfer matching: two new techniques for image matching
IJCAI'77 Proceedings of the 5th international joint conference on Artificial intelligence - Volume 2
Using signing space as a representation for sign language processing
GW'05 Proceedings of the 6th international conference on Gesture in Human-Computer Interaction and Simulation
Design and evaluation of classifier for identifying sign language videos in video sharing sites
Proceedings of the 14th international ACM SIGACCESS conference on Computers and accessibility
Identifying Sign Language Videos in Video Sharing Sites
ACM Transactions on Accessible Computing (TACCESS)
| Hi-index | 0.00 |
A major part of any sign language interpreter is the identification of the posture of the signer's hand. This is a complicated task due to the large variety of postures and orientations that a human hand can achieve. In this paper we present a method that we are implementing as part of an overall Irish sign language interpreter. Our method uses a set of three-dimensional hand models that are orientated at run time to match the orientation of a signer's hand. The orientation is defined by a pre-existing feature of our overall Sign Language Interpreter System. These models are then rendered to create a set of silhouettes for matching against a signer's hand silhouette that is extracted from the image. To overcome the problem of loosing finger information in a silhouette, we make use of a stereo camera setup to match two silhouettes created from images taken at two diverse angles. The matching is done using a Chamfer Distance algorithm, to determine the closeness of a match. Using a hand path identifier, which forms part of the Irish Sign Language Interpreter, we are able to reduce the set of postures under consideration. This reduces the number of comparisons needed during matching. We show that the use of our stereo image system enables us to achieve improved performance over a single camera setup and achieve a more reliable match.