Paper Info
Title
Authenticating corrupted face image based on noise model
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 Jung1131.68
Bon-Woo Hwang217716.33
Seong-Whan Lee33756343.90