Transfer Learning on Convolutional Neural Networks for Dog Identification

Abstract

This paper considers application of machine learning in the context of animal identity management for veterinary practice. In this application, electronic medical records of animals would include digital photographs that are used to identify them using image processing and recognition technologies. We investigated how combination of the “soft” biometrics such as breed, as well as face biometrics of dogs can improve identification of dogs. We apply transfer learning on GoogLeNet to perform the breed classification on the proposed BreedNet, and then to identify individual dogs within the classified breeds, on the proposed DogNet.