Paper Info
Title
Face Hallucination via Using the Graph-Optimal Locality Preserving Projections
Abstract
In the existing face hallucination approach using Locality Preserving Projections (LPP), the weight in neighborhood graph is artificially predefined, and this scheme does not benefit for subsequent learning process. That may bring about some uncertainty situation in the performance of algorithm. In this paper we use a novel dimension reduction algorithm called Graph-optimized Locality Preserving Projections(GoLPP), which takes construction of neighborhood graph in a optimal way. Then, Generalized Regression Neural Network (GRNN) is used to predict the global high resolution face image. However, the face image obtained by GRNN is smooth and lack of high frequency information. To enhance the image visual quality, a patch based Residual model is adopted. Experiment results show that the proposed approach can reconstruct high resolution face image efficiently, and the performance is better than other methods based LPP.
Year
DOI
Venue
2011
10.1109/ICIS.2011.36
ACIS-ICIS
Keywords
Field
DocType
global high resolution face,face image,existing face hallucination approach,graph-optimal locality preserving projections,high frequency information,face hallucination,novel dimension reduction algorithm,image visual quality,neighborhood graph,high resolution face image,locality preserving projections,face,manifolds,image resolution,mathematical model,image reconstruction,lpp,psnr
Iterative reconstruction,Residual,Computer vision,Locality,Face hallucination,Dimensionality reduction,Pattern recognition,Computer science,Artificial intelligence,Artificial neural network,Image resolution,Manifold
Conference
Citations 
PageRank 
References 
0
0.34
6
Authors
5
Name
Order
Citations
PageRank
Rongfang Yang100.68
Yunqiong Wang2302.59
Deqiang Yang300.68
Tianwei Xu4195.29
Juxiang Zhou553.13