Abstract | ||
---|---|---|
This paper presents our method for reconstructing facial image from a partially occluded facial image or a low-resolution one using example-based learning Faces are modeled by linear combinations of prototypes of shape and texture With the shape and texture information from an input facial image, we can estimate optimal coefficients for linear combinations of prototypes of shape and texture by simple projection for least square minimization The encouraging results of the proposed method show that our method can be used to improve the performance of the face recognition by reconstructing facial image from a partially occluded facial image or a low-resolution one. |
Year | DOI | Venue |
---|---|---|
2004 | 10.1007/978-3-540-30548-4_44 | SINOBIOMETRICS |
Keywords | Field | DocType |
linear combination,texture information,face recognition,optimal coefficient,encouraging result,square minimization,simple projection,proposed method show,facial image,input facial image,least square,low resolution | Iterative reconstruction,Virtual image,Least squares,Linear combination,Facial recognition system,Computer vision,Image texture,Computer science,Artificial intelligence,Biometrics,Image resolution | Conference |
Volume | ISSN | ISBN |
3338 | 0302-9743 | 3-540-24029-2 |
Citations | PageRank | References |
2 | 0.45 | 8 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Seong-Whan Lee | 1 | 3756 | 343.90 |
Jeong-seon Park | 2 | 202 | 18.13 |
Bon-Woo Hwang | 3 | 177 | 16.33 |