Analysis of pig facial images could help farmers

Animal behaviourists from Scotland’s Rural College Pig Research Centre and machine vision experts at the University of the West of England are collaborating to capture and analyse 3D and 2D facial images of breeding sows under various conditions that are likely to result in different emotional states including pain and stress. Pigs are highly expressive animals, and previous research has indicated that they can communicate with other pigs using different facial expressions. The images are processed at UWE Bristol’s Centre for Machine Vision, where various machine learning techniques are being developed to recognise various emotions from particular facial expressions. Once these learning techniques have been validated, the team will develop the technology for use on the farm for uninterrupted monitoring of individual sows in large herds to alert farmers to any health and welfare issues.
Professor Melvyn Smith, UWE Bristol’s Centre for Machine Vision, said: “Machine vision technology offers the potential to realise a low-cost, non-intrusive and practical means to biometrically identify individual animals on the farm. Our work has already demonstrated a 97% accuracy at facial recognition in pigs. Our next step will be, for the first time, to explore the potential for using machine vision to automatically recognise facial expressions that are linked with core emotion states, such as happiness or distress, in the identified pigs.”