| Popis: |
Assessing pain levels in animals is a crucial but time-consuming process in maintaining their welfare. Facial expressions in sheep are an efficient and reliable indicator of pain levels. We have extended techniques for recognising human facial expressions to analyse facial expressions of sheep, which can then facilitate automatic estimation of pain levels. In this chapter we describe our multilevel approach that starts with detection of sheep faces in an image, localisation of facial landmarks, normalisation and then extraction of facial features. Using machine learning methods, we then estimate the pain level from the detected change in the facial expressions. Our sheep face detection approach has been shown to be robust in detecting sheep faces in images containing many sheep, in different lighting conditions and with reasonable variation in viewpoints. We argue that our approach to automated pain level assessment can be generalised to other animals. |
