Multi-angle facial image analysis
Abstract
Fetal Alcohol Syndrome (FAS) is a developmental disorder caused by maternal drinking during pregnancy. Computerized imaging techniques have been applied to study human facial dysmorphology associated with FAS. This thesis mainly describes two new facial image analysis methods: the first method is based on a multi-angle image classification technique using micro-video images of mouse embryo, images taken from several different angles and analyzed separately, and the results are combined for classifications; The second method is to classify mouse embryos by using the isosurface information of mouse volume which is composed by multi-angle image slices, the information include discrete Gaussian curvature and Mean curvature of the isosurface mesh and the mesh area, and then using these data to extract features and make pattern recognition. Analysis results from animal models provide critical references for the understanding of FAS and potential therapy solutions for human patients.
Degree
M.S.
Advisors
Fang, Purdue University.
Subject Area
Computer science
Off-Campus Purdue Users:
To access this dissertation, please log in to our
proxy server.