Chimpanzee face recognition from videos in the wild using deep learning

Evaluation was performed on a held-out test set using the standard protocol outlined by Everingham et al. (39). The precision/recall curve was computed from a method's ranked output. Recall was defined as the proportion of all positive examples ranked above a given rank, while precision is the proportion of all examples above that rank which are from the positive class. For the purpose of our task, high recall was more important than high precision (i.e., false positives are less dangerous than false negatives) to ensure no chimpanzee face detections were missed. Some false positives, such as the recognition of chimpanzee behinds as faces (e.g., fig.