Training computers to recognise dogs and cats

Computer scientists at the University of Oxford, England, and International Institute of Information Technology (IIIT), Hyderabad, are working on making computers better at distinguishing cats and dogs from each other and different breeds of their species as well. These computers will be able to automatically recognise different cats and dogs.

The biggest problem that the scientists are encountering is that these animals come in different shapes and sizes. The team explained that researchers have often focussed on cats and dogs for which recognition and detection is particularly challenging. The team conducted two studies to help them in their endeavour.

“Beyond the technical interest of fine grained categorisation, extracting information from images of pets has a practical side too. People devote a lot of attention to their domestic animals, as suggested by the large number of social networks dedicated to the sharing of images of cats and dogs: Pet Finder, Catster, Dogster, My Cat Space, My Dog Space, The International Cat Association and several others. In fact, the bulk of the data used in this paper has been extracted from annotated images that users of these social sites post daily. It is not unusual for owners to believe (and post) the incorrect breed for their pet, so having a method of automated classification could provide a gentle way of alerting them to such errors,” said one of the team members.