As computer and database technologies advance rapidly, biologists all over the world can share biologically meaningful data from images of specimens and use the data to classify the specimens taxonomically. Accurate shape analysis of a specimen from multiple views of 2D images is crucial for finding diagnostic features using geometric morphometric techniques. We propose an integrated feature selection and clustering framework that automatically identifies a set of feature variables to group specimens into a binary cluster tree. The candidate features are generated from reconstructed 3D shape and local saliency characteristics from 2D images of the specimen. We use a mixture model to estimate the significance value of each feature and control the false discovery rate in the feature selection process so that the clustering algorithm can efficiently partition the specimen samples into clusters that may correspond to different species. The experiments on a taxonomic problem involving species of suckers in the genus Carpiodes demonstrate promising results using the proposed framework with small sample size.

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

It is estimated that ninety percent of the world's species have yet to be discovered and described. The main reason for the slow pace of new species description is that the science of taxonomy, as traditionally practiced, can be very laborious. To formally describe a new species, taxonomists have to manually gather and analyze data from large numbers of specimens, often from broad geographic areas, and identify the smallest subset of external body characters that uniquely diagnoses the new species as distinct from all its known relatives. In this paper, we use an automated feature selection and classification approach to address the taxonomic impediment in new species discovery. The experiments on a taxonomic problem involving species of suckers in the genus Carpiodes demonstrate promising results.