Thornycroft, Rosanne E. and Booth, Anthony J. (2012) Computer-aided identification of coelacanths, Latimeria chalumnae, using scale patterns. Marine Biology Research, 8 (3). pp. 300-306. DOI 10.1080/17451000.2011.628679.

Text THORNYCROFT.pdf - Reprinted Version Restricted to Registered users only Download (656kB)

Abstract

Despite coelacanths, Latimeria chalumnae, being listed as either endangered by CITES or critically endangered by the IUCN, their population size within South Africa is unknown and still needs to be estimated. Their conservation status unfortunately excludes the use of conventional tagging to mark individual animals for a possible mark–recapture experiment. This study shows that because coelacanths have a unique spot patterning it is possible to quickly and accurately identify specific individuals photographically using computer-aided identification software. Without any manual intervention by an operator, the software accurately identified between 56 and 92% of the individuals. Indentification success increased to 100% if the operator could also manually select from other potential matching photographs. It was also shown that fish exhibiting a yaw angle not exceeding 60° could be accurately identified in photographs, although the percentage of fish correctly identified without operator-intervention decreased rapidly with increasing yaw angle. Computer-aided identification should therefore facilitate future coelacanth research as it is both efficient and accurate while also reducing potential stress on the animals observed.

Actions (login required)

View Item