In light of the uncertainty surrounding flipper banding in some species, there is growing interest in alternative penguin identification methods that minimise disturbance but still allow for robust population monitoring. We have previously reported on the development of a prototype computer vision system that automatically identifies individual African penguins Spheniscus demersus using natural markings.
Here we demonstrate the potential for fully-automated, non-invasive, monitoring in the field at Robben Island, South Africa. False individual identifications of detected penguins occurred in less than 0.01% of comparisons (n = 73,600) to known individuals. The monitoring capacity in the field was estimated to be above 13% of the birds that passed the camera (n = 1453), with a significant increase under favourable conditions. Theoretical and empirical development of this capacity suggests high levels of enrolment and recapture over time frames of a few months. Finally, we present results from captive birds that confirm the long-term stability of the adult plumage pattern. In conclusion, the demonstrated sensitivity is comparable to computer-aided animal biometric monitoring systems in the literature, while a full deployment of the system would identify more penguins than is possible with complete exploitation of the current levels of flipper banding at Robben Island.