Paper Info
Title
Reconstructing a whole face image from a partially damaged or occluded image by multiple matching
Abstract
The problem we address in this paper is, given a facial image that is partially occluded or damaged by noise, to reconstruct a whole face. A key process for the reconstruction is to obtain the correspondences between the input image and the reference face. We present a method that matches an input image with multiple example images that are generated from a morphable face model. From the matched feature points, shape and texture of the full face are inferred by the non-iterative data completion algorithm. Compared with single matching with the particular "reference face", this multiple matching method increases the robustness of the matching. The experimental results of applying the algorithm to face images that are contaminated by Gaussian noise and those which are partially occluded show that the reconstructed faces are plausible and similar to the original ones.
Year
DOI
Venue
2007
10.1007/978-3-540-74549-5_73
ICB
Keywords
Field
DocType
reconstructed face,full face,whole face,morphable face model,multiple example image,single matching,multiple matching method,input image,whole face image,facial image,occluded image,reference face,gaussian noise
Computer vision,Pattern recognition,Computer science,Robustness (computer science),Artificial intelligence,Gaussian noise
Conference
Volume
ISSN
ISBN
4642
0302-9743
3-540-74548-3
Citations 
PageRank 
References 
2
0.39
10
Authors
2
Name
Order
Citations
PageRank
Bon-Woo Hwang117716.33
Seong-Whan Lee23756343.90