Shape-Based Retrieval of 3D Craniofacial Data

The goal of this work is to provide tools for the study of craniofacial anatomy from either CT scans or from a 12-camera active stereo photogrammetry system. Our image-analysis tools provide low-level operators for working with 3D craniofacial data. Our feature extraction tools produce quantitative representations (descriptors) of the 3D data that can be used to summarize the 3D shape with respect to the condition being studied and the question being asked. Similarity measure tools compare the data from two individuals (or between an individual and the average of a population) and produce a numeric similarity score. Organizational tools provide an image indexing mechanism that allows rapid retrieval of all images in a database that are similar to a query image in order of similarity. Finally, our user interface tools allow users to easily pose queries specifying both relational constraints on alphanumeric data and similarity constraints on image data in order to find subjects in a database who are most similar to a query subject with respect to studies from multiple different imaging modalities.

We will apply our tools for analysis, description, similarity measurement, organization and shape-based retrieval to a database of patients with midface hypoplasia and cleft lip and/or palate as part of the NIH/NIDCR FaceBase Consortium.
(Faculty: Shapiro)