3D face reconstruction is a very challenging problem in computer vision, and is used as a prerequisite for many important vision tasks, e.g., face recognition and face frontalization. The importance of 3D face reconstruction is that we can estimate illumination and pose information by using the 3D shape of the face. Since the human face is a non-rigid 3D object, estimating the 2D shape of the f...

Invariant features play a key role in object and pattern recognition studies. Features that are invariant to geometrical transformations offer succinct representations of underlying objects so that they can be reliably identified. In this dissertation, we introduce a family of novel invariant features based on Cartan’s theory of moving frames. We call these new features summation invariants. Co...

MIAO, SHUN. 3D Face Recognition From Range Image. (Under the direction of Professor Hamid Krim). In this thesis, we explore the statistical and geometrical behavior of the uncontrolled parameters of a human face, including both the rigid transform caused by a head pose and the non-rigid transform caused by a facial expression. We focus on developing a 3D facial recognition scheme which is robus...

This paper proposes an analysis-by-synthesis framework for face recognition with variant pose, illumination and expression. First, an efficient 2D-to3D integrated face reconstruction approach is introduced to reconstruct a personalized 3D face model from a single frontal face image with neutral expression and normal illumination; Then, realistic virtual faces with different of pose, illuminatio...

In this paper we propose a system for 3D face reconstruction from 2D stereo images. Two different stereo matching algorithms are presented; the first is a local method that finds the correspondences of 15 most characteristic facial fiducial points, whose 3D reconstruction allows us to deform a parameterized sparse model. The second method employs a snake grid algorithm which minimizes a multi-r...

This paper explores the use of multi-instance enrollment as a means to improve the performance of 3D face recognition. Experiments are performed using the ND-2006 3D face data set which contains 13,450 scans of 888 subjects. This is the largest 3D face data set currently available and contains a substantial amount of varied facial expression. Results indicate that the multi-instance enrollment ...

A novel 3D face recognition framework based on Multiple Kernel Learning (MKL) is proposed in this work. As a first step, preprocessing is applied in order to extract relevant information and remove noise from 3D face scans. Next, a surface normals and Locally Adaptive Regression Kernels (LARK) features are extracted and a kernel function is associated with them. Finally, the corresponding kerne...

The use of Three Dimensional (3D) data allows new facial recognition algorithms to overcome factors such as pose and illumination variations which have plagued traditional 2D Face Recognition. In this paper a new method for providing insensitivity to expression variation in range images based on Log-Gabor Templates is presented. By decomposing a single image of a subject into 147 observations t...

This paper addresses face recognition under varying light via 3D reconstruction based on the techniques of shape from shading (SFS). First, we improve the geometric-based SFS by introducing the integrability constraint as one of the regular terms. This operation preserves the local curvedness of the recovered surface. Second, we propose a novel method to investigate human face recognition in th...

Conventional 2D face recognition methods often struggle when a subject's head is turned even slightly to the side. In this study, a face recognition system based on 3D head modeling that is able to tolerate facial rotation angles was constructed by leveraging the Open source graphic library (OpenGL) framework. To minimize the extensive angle searching time that often occurs in conventional 3D m...