Abstract | ||
---|---|---|
An analysis-by-synthesis framework for face recognition with variant pose, illumination and expression (PIE) is proposed in this paper. First, an efficient 2D-to-3D 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 PIE are synthesized based on the personalized 3D face to characterize the face subspace. Finally, face recognition is conducted based on these representative virtual faces. Compared with other related works, this framework has the following advantages: 1) only one single frontal face is required for face recognition, which avoids the burdensome enrollment work; 2) the synthesized face samples provide the capability to conduct recognition under difficult conditions like complex PIE; and 3) the proposed 2D-to-3D integrated face reconstruction approach is fully automatic and more efficient. The extensive experimental results show that the synthesized virtual faces significantly improve the accuracy of face recognition with variant PIE. |
Year | DOI | Venue |
---|---|---|
2004 | 10.1109/AFGR.2004.1301639 | FGR |
Keywords | Field | DocType |
single frontal face image,2d-to-3d integrated face reconstruction,face subspace,image pose,image illumination,realistic virtual face,single frontal face,face recognition,complex pie,synthesized face sample,integrated face reconstruction approach,image expression,image reconstruction,representative virtual face,virtual faces,face model,automatic 3d reconstruction,face detection,3d reconstruction,pattern recognition,lighting,shape,analysis by synthesis,art,system testing | Iterative reconstruction,Computer vision,Facial recognition system,Face hallucination,Three-dimensional face recognition,Object-class detection,Pattern recognition,Subspace topology,Computer science,Artificial intelligence,Face detection,3D reconstruction | Conference |
ISBN | Citations | PageRank |
0-7695-2122-3 | 65 | 3.64 |
References | Authors | |
12 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yuxiao Hu | 1 | 2209 | 103.06 |
Dalong Jiang | 2 | 203 | 10.26 |
Shuicheng Yan | 3 | 65 | 3.64 |
Lei Zhang | 4 | 2533 | 164.29 |
Hong-Jiang ZHANG | 5 | 17378 | 1393.22 |