The aim of our research is to investigate visual object recognition in experts. In particular we are interested in expert perception of natural objects and scene rather than 'novice' or normal perception. Expert perception is characterised by a period of training, which is required to ensure that perceptions meet the criteria for expert behaviour. Projects include expert plankton categorisation and cytological smear slide assessment.

Penilia avirostris Cladocera from HAB2.2005-07-22.1021.N534

Since 1989 the Natural Object Categorisation group at Plymouth University have been developing machine vision systems to categorise marine plankton. The group have focussed on the difficult task of discriminating microplankton, as it is a good model for investigating top-down influences of expert judgements on bottom-up processes. It has been particularly revealing to explore the issues of recognition in a target group of objects where natural morphological variation within species causes experts difficulties.

Four operational machines (called HAB Buoy) have been constructed and deployed to marine laboratories in the Rías of north Spain, The gulf of Trieste in Italy and Galway Bay in Ireland, as well as here in Plymouth. HAB Buoy is being extensively tested in the laboratory and in situ with field-collected specimens of a wide range of plankton species, from fish larvae and mesozooplankton to the dinoflagellates of the microplankton. HAB Buoy employs multi-resolution processing, ‘what and where' coarse channel analysis with support vector machine categorisation.

Oithona VI female Copepod from HAB2.2005-07-22.1021.N2749

Recent work into weak and unsupervised learning of plankton species, using data mining techniques, is offering a new way of extending the labelling robustness of HAB Buoy.

Projects include expert plankton categorisation, motion analysis, texture processing and cytological smear slide assessment.

For further information please click here to visit the Natural Object Categorisation Website (link opens in new window).

To contact this group please email Dr Philip Culverhouse: PCulverhouse@Plymouth.ac.uk.