Abstract | ||
---|---|---|
In this paper, we propose a method for authenticating corrupted face images based on noise model. The proposed method first generates corrupteed images by controlling nois parameters in the training phase. The corrupted images and noise parameters are represented by a linear combination of prototypes of the corrupted images and the noise parameters. With the corrupted image and an original image, we can estimate noise parameters of the corrupted face image in the testing phase. Then, we can make a synthesized face image from the original face image with the estimated noise parameters and verify it with the corrupted face image. Our experimental results show that the proposed method can estimate noise parameters accurately and improve the performance of face authentication. |
Year | DOI | Venue |
---|---|---|
2004 | 10.1109/AFGR.2004.1301543 | FGR |
Keywords | Field | DocType |
noise parameter,face recognition,noise,noise model,corrupted image,original face image,image denoising,original image,noise parameters estimation,corrupted face image,image reconstruction,face authentication,synthesized face image,principal component analysis,corrupted face images authentication,estimated noise parameter,smart cards,feature extraction,face detection,parameter estimation,computer science,authentication,phase noise | Iterative reconstruction,Facial recognition system,Linear combination,Computer vision,Authentication,Pattern recognition,Computer science,Image based,Dark-frame subtraction,Image noise,Artificial intelligence,Principal component analysis | Conference |
ISBN | Citations | PageRank |
0-7695-2122-3 | 7 | 0.55 |
References | Authors | |
10 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ho-Choul Jung | 1 | 13 | 1.68 |
Bon-Woo Hwang | 2 | 177 | 16.33 |
Seong-Whan Lee | 3 | 3756 | 343.90 |