Revisiting giraffe photo-identification using deep learning and network analysis

An increasing number of research programs rely on photographic capture-recapture (vs. direct marking) of individuals to study distribution and demography within animal populations. Photo-identification of individuals living in the wild is sometimes feasible using idiosyncratic coat or skin patterns, like for giraffes. When performed manually, the task is tedious and becomes almost impossible as populations grow in size. Computer vision techniques are an appealing and unavoidable help to tackle this apparently simple task in the big-data era. In this context, we propose to revisit giraffe re-identification using convolutional neural networks (CNNs).We first developed an end-to-end pipeline to retrieve a comprehensive set of re-identified giraffes from about 4, 000 raw photographs. To do so, we combined CNN-based object detection, SIFT pattern matching, and image similarity networks. We then quantified the performance of deep metric learning to retrieve the identity of known and unknown individuals. The re-identification performance of CNNs reached a top 5 accuracy of about 90%. Fully based on open-source software packages, our work paves the way for further attempts to build CNN-based pipelines for re-identification of individual animals, in giraffes but also in other species.