Skip to main content
5 September 2019

Latest News

St Hugh’s researchers use AI to recognise and track primate faces

Scientists affiliated with St Hugh’s College have contributed to the development of AI-driven software that is capable of tracking the faces of primates like chimpanzees in the wild.

10 million images and video footage were used to train the computer model to identify and track the faces of specific animals, which will be invaluable to researchers, dramatically cutting back on the time required to analyse video footage.

Co-author of the study Dan Schofield, a DPhil student at the Primate Models Lab in the School of Anthropology, said:

“For species like chimpanzees, which have complex social lives and live for many years, getting snapshots of their behaviour from short-term field research can only tell us so much.

“By harnessing the power of machine learning to unlock large video archives, it makes it feasible to measure behaviour over the long term, for example observing how the social interactions of a group change over several generations.”

The study was co-authored by Dan’s supervisors, Professor Dora Biro and Professor Susana Carvalho, both of whom are Fellows of St Hugh’s College.

The paper can be read here and the University news story here.

Share this post

Related News Posts

The Colin Matthew Fund 2024 is open to applications
This fund offers travel awards for historical research to all undergraduate and graduate members of the University of Oxford. Professor Coli...
Read More
Research by St Hugh’s Fellow suggests that having employees with disabilities is a source of competitive advantage for organisations
Professor Luisa Alemany, St Hugh's Fellow by Resolution in Management is the co-author of some ground-breaking research which suggests that having emp...
Read More
St Hugh’s MCR celebrate students’ cutting-edge research
As her tenure as MCR Academic Representative comes to an end, Caroline Taylor (third year DPhil, English) reflects on the past year's MCR activities ...
Read More