Computer-aided identification of coelacanths, Latimeria chalumnae, using scale patterns

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