Bowei Xi is an Assistant Professor in the Department of Statistics at Purdue University. Xiadong Yang is a Postdoctoral Fellow at Kansas State University. Vijayan N. Nair is D.A. Darling Professor of Statistics and Professor of Industrial and Operations Engineering at the University of Michigan. George Michailidis (corresponding author) is Professor of Statistics, Electrical Engineering and Com...

We present a novel 3D face recognition approach based on geometric invariants introduced by Elad and Kimmel. The key idea of the proposed algorithm is a representation of the facial surface, invariant to isometric deformations, such as those resulting from different expressions and postures of the face. The obtained geometric invariants allow mapping 2D facial texture images into special images...

Finding landmark positions on facial images is an important step in face registration and normalization, for both 2D and 3D face recognition. In this paper, we inspect shortcomings of existing approaches in the literature and compare several methods for performing automatic landmarking on near-frontal faces in different scales. Two novel methods have been employed to analyze facial features in ...

Malposition of venous cannula can cause inadequate venous drainage during cardiopulmonary bypass. It would be good clinical practice to use TEE to check the position of inferior venous cannula to avoid this problem at the earliest.

There have been significant advancements in the ability of echocardiography to provide both morphological and functional information in children with congenitally malformed hearts. This progress has come through the development of improved technology such as matrix array probes and software which allows for the off line analysis of images to a high standard. This article focuses on these develo...

In this paper we propose a fully automatic scheme for 3D face recognition. In our scheme, the original 3D data is automatically converted into the normalized 3D data, then the discriminant common vector (DCV) is introduced for 3D face recognition. We also compare DCV with two common methods, i.e., principal component analysis (PCA) and linear discriminant analysis (LDA). Our experiments are bas...

A problem in three-dimensional imaging by a confocal scanning laser microscope (CSLM) in the (epi))uorescence mode is the darkening of the deeper layers due to absorption and scattering of both the excitation and the uorescence light. In this paper we propose a new method to correct for these eeects. Our approach, valid for weak attenuation, consists in multiplying the measured uorescent intens...