A STATISTICAL MODEL COMBINING SHAPE AND SPHERICAL HARMONICS FOR FACE RECONSTRUCTION AND RECOGNITION

被引：0

作者：

Rara, H. ^{[1
]}

Elhabian, S. ^{[1
]}

Starr, T. ^{[1
]}

Farag, A. ^{[1
]}

机构：

[1] Univ Louisville, CVIP Lab, Louisville, KY 40292 USA

来源：

2008 CAIRO INTERNATIONAL BIOMEDICAL ENGINEERING CONFERENCE | 2008年

关键词：

Face reconstruction; recognition; illumination;

D O I：

暂无

中图分类号：

R318 [生物医学工程];

学科分类号：

0831 ;

摘要：

We describe a face reconstruction framework based on a statistical model that combines shape (2D and height maps), appearance (albedo), and spherical harmonics projection (SHP) information. The framework takes a 2D frontal face image under arbitrary illumination as input and outputs the estimated 3D shape and appearance. Face identification is performed using the shape and albedo coefficients of the fitting process, as well as the actual shape/texture reconstructions. Results indicate decent face reconstructions and a perfect recognition rate for the frontal images of the Extended Yale Database B.

引用

页码：11 / 14

页数：4

共 15 条

[1]

AHMED A, 2007, NEW STAT MODEL COMBI

[2]

[Anonymous], ACTIVE APPEARANCE MO

[3] Lambertian reflectance and linear subspaces [J].