The Green Toad example: a comparison of pattern recognition software

Publications: Contribution to journalArticlePeer Reviewed

Abstract

Individual identification of animals is important for assessing the size and status of populations. Photo-based approaches,
where animals are recognized by naturally occurring and visually identifiable features, such as color patterns, are cost-effective
methods for this purpose. We compared five available programs (Wild-ID, Hotspotter, AmphIdent, APHIS, I3S Pattern+) for their
power to semi-automatically identify dorsal patterns of the European green toad (Bufotes viridis). We created a data set of 200
pictures of known identity, two pictures for each individual, and analyzed the percentage of correctly identified animals for each
software. Furthermore, we employed a generalized linear mixed model to identify important factors contributing to correct
identifications. We used these results to estimate the population size of our hypothetical population. The freely available HotSpotter
application performed best, identifying close to 100 % of the photos correctly. Females had a higher chance of recognition,
presumably because of sex-specific differences in the pattern contrast. Population estimates were close to the expected 100 for
HotSpotter, but for the other applications population size was highly overestimated. Given the clarity of our results we strongly
recommend the HotSpotter software, which is a highly efficient tool for individual pattern recognition.
Original languageEnglish
Article numbere211506
Pages (from-to)96-99
Number of pages4
JournalNorth-Western Journal of Zoology
Volume17
Issue number1
Publication statusPublished - 25 Mar 2021

Austrian Fields of Science 2012

  • 106047 Animal ecology

Keywords

  • Amphibia, color pattern, photo-identification software, population statistics, recapture study

Cite this