Research Areas

ISIS is a multi-disciplinary group, with research in four distinctive areas.

• Image Processing and Computer Vision

  The ISIS research in image processing and computer vision spans techniques from preprocessing, to feature extraction (especially moving ones) and on to image analysis. Our main application domains have been in biometrics, in remote sensing and in medical image analysis. We have a long record in biometrics, starting in face recognition, and have since conducted some of the earliest work in recognising people by their gait and by their ears.

• Speech Science and Technology

  Reflecting our philosophy that powerful speech systems of the future will be based on a thorough understanding of the fundamental science, ISIS research in speech processing ranges from basic science underpinning production and perception, through to applications in bio-medicine and improved human-computer interaction. Research topics include: modelling speech aeroacoustics, classification of speech sounds, evolutionary emergence of speech and language, computational models of humanspeech and language processing, vocal tract imaging, transduction problems in speech synthesis.

• Intelligent Systems and Machine Learning

  In our ever-increasing information age, advanced intelligent systems are required to manage and understand enormous amounts of data, and to learn their salient characteristics. ISIS work in Intelligent Systems and Machine Learning is diverse, ranging from the development of new theories through to their application in fields such as signal processing, vision, materials science, medical, automotive, nautical and aerospace. The theoretical research includes:

  • Modelling Evolutionary Algorithms
  • Intelligent Data Modelling
  • Data Fusion
  • Support Vector Machines and Kernel-based Learning
  • Data Mining and Knowledge Discovery
  • Bioinformatics, chemoinformatics and proteomics
• Systems and Control

  Our research on systems and control is focussed on basic theoretical development, verification, and validation of data modeling and control approaches. Specific topics of interest are:

  • Behavioural systems theory
  • Iterative learning control
  • Robust nonlinear control
  • Adaptive control
  • Identification
  • Flow control
  • Multidimensional (nD) systems