Pattern recognition in animals and machines: using machine learning to reveal cues central to the identification of individuals (2014–2017)

Abstract:
The power to recognise individuals of a species requires significant image and pattern discrimination abilities. Yet, individual recognition has been found in a huge range of species, from humans to invertebrates demonstrating its importance for social interactions. We will investigate this ability in lower vertebrates (fish, with no visual cortex), so as to understand the underlying mechanisms of pattern discrimination. We will also test how robust this ability is during changes in water quality (elevated CO2 levels and increased turbidity). Outcomes will further our knowledge base in lower vertebrate vision and evolution, and also have implications for human vision, image analysis, and artificial vision.
Grant type:
ARC Discovery Projects
Researchers:
  • Professor
    School of Human Movement and Nutrition Sciences
    Faculty of Health and Behavioural Sciences
Funded by:
Australian Research Council