In a study by German et al. (2018), it was found that canine obesity affects 74% of adult dogs. This is concerning given that overweight dogs “have a shortened life span, their quality of life is adversely affected, and they are predisposed to other conditions including osteoarthritis, diabetes mellitus and certain types of neoplasia”.

Unfortunately determining whether a dog is overweight or obese is subjective and there are often differences in opinions by owners and even by veterinarians. As such an automated system using machine learning technology would remove this bias allowing quick, cheap and safe evaluation of body condition scores whilst offering a solution to help tackle canine obesity. Further information regarding the ongoing development of the project can be found on the project blog.

Thank you to everyone that provided photographs of your dogs for training the model and a sample model has been created for Labrador Retrievers.

German, A.J., Woods, G.R.T., Holden, S.L., Brennan, L., & Burke, C. (2018). Dangerous trends in pet obesity. The Veterinary record, 182(1), 25. https://doi.org/10.1136/vr.k2