Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/33493
Title: Learning local pixel structure for face hallucination
Authors: Hu, Y
Lam, KM 
Qiu, GP
Shen, TZ
Tai, H
Keywords: TV norm
Face hallucination
Local pixel structure
Super resolution
Issue Date: 2010
Publisher: IEEE
Source: 2010 17th IEEE International Conference on Image Processing (ICIP), 26-29 September 2010, Hong Kong, p. 2797-2800 How to cite?
Abstract: In this paper, we present a novel learning-based face hallucination method based on the assumption that similar faces will have similar local pixel structures. We use the low- resolution (LR) input face to search a database for K example faces that are the most similar to the input and align them with the input accordingly. The local pixel structures of the target high-resolution (HR) image are learned from those warped HR example faces in a neighbor embedding manner, and a total variation (TV) constraint is employed to aid the learning of all pixels' embedding weights. The learned local pixel structures are then used as constraints to reconstruct a HR version of the input face. Experimental results show that the method performs well in terms of both reconstruction error and visual quality.
URI: http://hdl.handle.net/10397/33493
ISBN: 978-1-4244-7992-4
978-1-4244-7993-1 (E-ISBN)
ISSN: 1522-4880
DOI: 10.1109/ICIP.2010.5651052
Appears in Collections:Conference Paper

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

1
Citations as of Apr 19, 2016

WEB OF SCIENCETM
Citations

1
Last Week
0
Last month
0
Citations as of Apr 20, 2017

Page view(s)

16
Last Week
0
Last month
Checked on Apr 23, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.