Monitoring of pet animal in smart cities using animal biometrics

Monitoring of pet animal in smart city is a big challenge for authorities concerned. The classical animal identification and monitoring methods fail to provide the required level of security and management of pet animals. Animal biometrics based recognition systems are considered a good alternative for the health management, tracking, identification, and security of pet animals. In this paper, we propose a low-cost system for monitoring of pet animals (dogs) based on their primary animal biometric identifiers. The proposed recognition approach uses the one-shot similarity and distance metric based learning methods for matching and classifying the extracted features of face images for recognition of pet animals (dog). We also developed a prototype for evaluating the accuracy of the recognition system. The efficacy of proposed pet animal recognition system is evaluated under identification settings yields 96.87% recognition rate.