Abstract | ||
---|---|---|
This paper proposes a method for reconstructing partially damaged faces based on a morphable face model. Faces are modeled by linear combinations of prototypes of shape and texture. With the shape and texture information from an undamaged region only, we can estimate optimal coefficients for linear combinations of prototypes of shape and texture by simple projection for least-square minimization (LSM). Our experimental results show that reconstructed faces are very natural and plausible like real photos. |
Year | DOI | Venue |
---|---|---|
2003 | 10.1109/TPAMI.2003.1182099 | IEEE Trans. Pattern Anal. Mach. Intell. |
Keywords | Field | DocType |
reconstructed face,linear combination,morphable face model,texture information,real photo,partially damaged face,optimal coefficient,simple projection,least-square minimization,undamaged region,indexing terms,vectors,least square,noise shaping,principal component analysis,minimisation,degradation,prototypes,face detection,shape,pixel,image reconstruction | Iterative reconstruction,Computer vision,Linear combination,Pattern recognition,Computer science,Noise shaping,Minification,Minimisation (psychology),Artificial intelligence,Pixel,Face detection,Principal component analysis | Journal |
Volume | Issue | ISSN |
25 | 3 | 0162-8828 |
Citations | PageRank | References |
62 | 3.09 | 6 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bon-Woo Hwang | 1 | 177 | 16.33 |
Seong-Whan Lee | 2 | 3756 | 343.90 |