Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 Machine Graphics and Vision

2 2003

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Representing the finger-only topology for hand shape recognition

Holden E. J., Owens R.

Machine Graphics and Vision

2003

Vol. 12, No. 2

187-202

Automatic recognition of hand shapes in a moving image sequence requires the elements of hand tracking, feature extraction and classification. We have developed a robust tracking algorithm and a new hand shape representation technique that characterises the finger-only topology of the hand by adapting an existing technique from speech signal processing. The tracking algorithm determines the centre of the largest convex subset of the hand throughout an image sequence, using a combination of pattern matching and condensation algorithms. A hand shape feature represents the topological formation of the finger-only regions of the hand using a Linear Predictive Coding parameter set called cepstral coefficients. Feature extraction is performed on the polar dimensions of the hand region-of-interest, by tracking the finger-only region and extracting euclidean distances between the finger-only contour and the hand centre, which are then converted into cepstral coefficients. Experiments are conducted using mug-grabbing sequences to recognise four different hand shapes. Results demonstrate the robustness of hand tracking on cluttered backgrounds and the effectiveness of the hand shape representation technique on varying hand shapes.

An Animated Auslan Tuition System

Yeates S., Holden E. J., Owens R.

Machine Graphics and Vision

2003

Vol. 12, No. 2

203-214

An Animated Auslan Tuition System uses a computer general signer to provide flexible, visual Australian Sign Language (Auslan) educational tool. Signs are generated and animated by our generig Human Modelling System that is implemented in cross-platform object-oriented C++. The Human Modelling System consists of three modules: the core Human Modelling Module for model construction, manipulation and forward kinetics; the Model Rendering Module for displaying model configuration visually using OpenGL; and the Model Interpolation Module, for providing flexible partial-keyframe interpolation and animation control. These modules form the basis of the Auslan Tuition System, and allow the display of categorised sign phrases, interactive fingerspelling and contextual sign dialogue examples. The user has complete viewing control of sign display and animation, running on modest hardware.