Computer-assisted photo-identification of individual marine vertebrates: a multi-species system

Abstract: A computer program named ‘Finscan’ was developed for identifying individual marine animals by comparing new photographic images with a collection of previously identified images. The matching process was based on the pattern of nicks and notches commonly found along the trailing edge of the dorsal fin of many delphinid species. The program also allowed the inclusion of other user-defined descriptive features, such as leading-edge notches and truncated or irregular shapes. The output of the system was a presentation of images selected from the database, shown in order of similarity to a query image, so that the user could confirm the match. Two algorithms for representing notch patterns were tested and compared and the system was evaluated with dorsal fin images of several marine vertebrates, as well as fluke images for one species. Using a database of images that were previously identified by expert observers, the performance of the system was measured in terms of the number of incorrect matches that were offered before the correct match. Since in most cases the correct match was offered as the first or one of the first suggestions, the program substantially reduced the amount of effort required to perform photo-based matching.


Document Type: Research article

Pages:  117-123

$12.00Add to cart