A string matching computer-assisted system for dolphin photoidentification

This paper presents a syntactic/semantic string representation scheme as we ll as a string matching method as part of a computer-assisted system to ide ntify dolphins from photographs of their dorsal fins. A low-level string re presentation is constructed from the curvature function of a dolphin's fin trailing edge, consisting of positive and negative curvature primitives. A high-level string representation is then built over the low-level string vi a merging appropriate groupings of primitives in order to have a less sensi tive representation to curvature fluctuations or noise. A family of syntact ic/semantic distance measures between two strings is introduced. A composit e distance measure is then defined and used as a dissimilarity measure for database search, highlighting both the syntax (structure or sequence) and s emantic (attribute or feature) differences. The syntax consists of an order ed sequence of significant protrusions and intrusions on the edge, while th e semantics consist of seven attributes extracted from the edge and its cur vature function-The matching results are reported for a database of 624 ima ges corresponding to 164 individual dolphins. The identification results in dicate that the developed string matching method performs better than the p revious matching methods including dorsal ratio, curvature, and curve match ing. The developed computer-assisted system can help marine mammalogists in their identification of dolphins, since it allows them to examine only a h andful of candidate images instead of the currently used manual searching o f the entire database. (C) 2000 Biomedical Engineering Society. [S0090-6964 (00)00510-5].