View Item 
        •   Utrecht University Student Theses Repository Home
        • UU Theses Repository
        • Theses
        • View Item
        •   Utrecht University Student Theses Repository Home
        • UU Theses Repository
        • Theses
        • View Item
        JavaScript is disabled for your browser. Some features of this site may not work without it.

        Browse

        All of UU Student Theses RepositoryBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

        Equine Utrecht University Scale for Automated Recognition in Facial Assessment of Pain - EQUUS-ARFAP

        Thumbnail
        View/Open
        Thesis.pdf (2.912Mb)
        Publication date
        2018
        Author
        Jonkers, B.
        Metadata
        Show full item record
        Summary
        The EQUUS-ARFAP, or the Equine Utrecht University Scale for Automated Recognition in Facial Assessment of Pain, is a project striving to lay the foundations for and prove the feasibility of an application that can automatically assess pain-levels in horses through facial photos. So far only one similar project exists that works on sheep, which is why this project aims to expand upon and broaden this field of automated pain recognition tools for animals and veterinary use. The theory behind the application is based on a combination of the EQUUS-FAP and the HGS pain scoring systems, combining their scoring systems into a single-moment facial-data only pain-scoring scale which is applicable on facial photographs of horses. To create a first version of this application several computer-vision based techniques were used that have been founded on human facial feature recognition. These have been altered to work on the facial features of horses, through the use of medical information available on them. Active shape models, histograms of gradients, colour space conversions, image thinning, support vector machines and cross validation are some of the techniques that were used to realize this application. Results comparable to those of a similar application have been achieved, so it can be safely concluded that this kind of application is feasible and that a basis for future research to continue from has been provided.
        URI
        https://studenttheses.uu.nl/handle/20.500.12932/29723
        Collections
        • Theses
        Utrecht university logo