Giant Panda Face Recognition Using Small Dataset

Giant panda (panda) is a highly endangered animal. Significant efforts and resources have been put on panda conservation. To measure effectiveness of conservation schemes, estimating its population size in wild is an important task. The current population estimation approaches, including capture-recapture, human visual identification and collection of DNA from hair or feces, are invasive, subjective, costly or even dangerous to the workers who perform these tasks in wild. Cameras have been widely installed in the regions where pandas live. It opens a new possibility for non-invasive image based panda recognition. Panda face recognition is naturally a small dataset problem, because of the number of pandas in the world and the number of qualified images captured by the cameras in each encounter. In this paper, a panda face recognition algorithm, which includes alignment, large feature set extraction and matching is proposed and evaluated on a dataset consisting of 163 images. The experimental results are encouraging.

1. INTRODUCTION

Recognition of individual animals is an important task, which allows researchers to understand animal’s behavior and study population parameters such as population size, movement patterns, etc. There exist invasive and non-invasive methods for the individual recognition. Invasive methods require capturing an animal and physical tagging, which is troublesome, costly and likely to cause stress. Non-invasive methods use biometric traits such as DNA collected from hair or feces; or visual assessment based on images taken by cameras mounted in inhabited regions. DNA collection is costly and in some cases infeasible because it requires conservation workers going to rural or dangerous areas to acquire the samples. Therefore, visual assessment and animal biometrics gained attention as a potential solution.