Integrated Feature Selection and Clustering from Multiple Views for a Taxonomic Problem

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.