Chimpanzee identification using global and local features
Because of the ongoing biodiversity crisis many species like chimpanzees or gorillas for example are threatened and need to be protected. To overcome this agitating issue, biologist recently started to use remote camera devices for wildlife monitoring and estimation of remaining population sizes. Unfortunately, the huge amount of data makes the necessary manual analysis extremely tedious and highly cost intensive. To reduce the burden of time consuming routine work, we have recently started to develop computer vision algorithms to identify individuals. In this paper we extend our previous work using both global and local information for identification. To combine the results of the two approaches we apply a decision based parallel fusion scheme where we take the confidences of both classifiers into account. We show that the proposed approach outperforms our previous work for full-frontal faces while at the same time being more robust against pose variations. We evaluate our algorithm on two datasets of captive and free-living chimpanzees. The outcome of this paper builds the basis of a semi-automatic identification system for African Great Apes which will help biologists to develop new and innovative protection strategies.