Craniofacial image analysis

Abstract

Craniofacial researchers have used anthropometric measurements taken directly on the human face for research and medical practice for decades. With the advancements in 3D imaging technologies, computational methods have been developed for the diagnoses of craniofacial syndromes and the analysis of the human face. Using advanced computer vision and image analysis techniques, diagnosis and quantification of craniofacial syndromes can be improved and automated. This paper describes a craniofacial image analysis pipeline and introduces the computational methods developed by the Multimedia Group at the University of Washington including data acquisition and preprocessing, low- and mid-level features, quantification, classification, and content-based retrieval.