Shark identification using the notches in the dorsal fin

[摘要] ENGLISH ABSTRACT : In order to protect endangered species, such as the Great White shark, a reliableestimate of the population is needed. In counting animals, it is necessary to beable to distinguish between individuals. The current procedure is manual photoidentification, which is a time consuming process. By automating this process,when a shark is spotted, it can easily be matched to an existing shark in thedatabase or added to the database as a new shark.Photo identification software is already available for animal species such aspenguins, elephants and dolphins. DARWIN, used for identification of dolphinswas tested on sharks, but found to be unsuccessful in matching an unknownshark in to the correct shark in the database. DARWIN also requires extensiveuser input, which is what we are trying to eliminate or greatly reduce in theidentification of sharks. In this thesis, Hidden Markov models (HMM) is usedto develop software to identify individual sharks. The results of the HMM wasthen compared to software using Dynamic Time Warping (DTW) to do thematching. The DTW program was able to correctly match 80% of the imageswithin a rank of twenty and 62% with a rank of two or less. Using HMM, 84%of the photographs were correctly matched with a rank of twenty or less, butonly 56% with a rank of two or less and 64% with a rank of five or less.Although the HMM does not perform as well as the DTW, much better performanceis expected from the HMM software by building up a quality databasethrough the visual inspection and inclusion of photographs that will lead tomore consistent models.

[发布机构] Stellenbosch University