"Finscan", a computer system for photographic identification of marine animals

Author

Hillman, G.R. ; Kehtarnavaz, Nasser ; Wursig, B. ; Araabi, B. ; Gailey, G. ; Weller, D. ; Mandava, S. ; Tagare, H.

Author_Institution

Univ. of Texas Med. Branch, Galveston, TX, USA

Volume

2

fYear

2002

fDate

2002

Firstpage

1065

Abstract

A system has been developed for computer-assisted photographic identification of marine animals. The system creates and maintains a database of images of dorsal fins or flukes, and the user queries it by entering a new image acquired in the field. The system searches the database for similar images based on the notching pattern of the dorsal fin or fluke, and offers a list of database members ordered by similarity to the query image. A syntactic/semantic string representation method is used for matching and is compared with matching by direct alignment of edge patterns. The system has been tested with data sets of images of several biological species.

Keywords

image recognition; string matching; visual databases; zoology; Finscan; computer-assisted photographic identification; dorsal fins; flukes; image database; marine animals; notching pattern; pattern recognition; photographic identification; syntactic/semantic string representation method; visual databases; zoology; Biomedical imaging; Catalogs; Dolphins; Image databases; Marine animals; Medical diagnostic imaging; Pattern matching; Testing; Tin; Whales;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology, 2002. 24th Annual Conference and the Annual Fall Meeting of the Biomedical Engineering Society EMBS/BMES Conference, 2002. Proceedings of the Second Joint

ISSN

1094-687X

Print_ISBN

0-7803-7612-9

Type

conf

DOI

10.1109/IEMBS.2002.1106279

Filename

1106279