The Machine Intelligence Laboratory focuses on speech processing and control applications, computer vision and robotics, and medical imaging. The guiding principle of all research in the laboratory is that a well-designed engineering system must be based on a sound mathematical model.
A wide range of applicable techniques include neural networks, stochastic processes such as hidden Markov models, Bayesian inference, invariant transformations in 3D geometry, computational geometry, Wiener and Kalman filtering, classification and regression trees, and genetic algorithms.
The principal areas of interest are as follows:
- 3D ultrasound acquisition and visualisation, ultrasound deconvolution and stiffness imaging, and osseous cortical thickness estimation in CT
- 3D models from uncalibrated images, object recognition, human-computer interfaces, visual tracking and localisation, and augmented reality
- Continuous speech recognition and transcription, spoken dialogue systems, synthesis and coding, and statistical machine translation