Taxonomy in Fish Species Complexes: A Role for Multimedia Information

Biologists could make valuable use of the wealth of specimen information in natural history museum databases. "Taxonomy via the Internet" aims to build a centralized database where biologists can store, manipulate and retrieve biologically meaningful data from images of specimens and use the data to classify the specimens taxonomically. Multimedia information representation provides a new computational tool for extracting useful features from large databases of specimen images and has potential to expedite the pace of taxonomic research. In this paper, we use a taxonomic problem involving species of suckers in the genus Carpiodes to demonstrate the utility of this method. Logistic regression classifier with fully automated feature selection procedure is compared with the best landmark based classifier to illustrate how image quality affects classification accuracy. We discuss the need of creating a multimedia database using images of specimens from a fish collection