Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/80065
Title: Face hallucination based on sparse local-pixel structure
Authors: Li, Y
Cai, C
Qiu, G
Lam, KM 
Keywords: Face hallucination
Sparse local-pixel structure
Sparse representation
Super-resolution
Issue Date: 2014
Publisher: Elsevier
Source: Pattern recognition, 2014, v. 47, no. 3, p. 1261-1270 How to cite?
Journal: Pattern recognition 
Abstract: In this paper, we propose a face-hallucination method, namely face hallucination based on sparse local-pixel structure. In our framework, a high resolution (HR) face is estimated from a single frame low resolution (LR) face with the help of the facial dataset. Unlike many existing face-hallucination methods such as the from local-pixel structure to global image super-resolution method (LPS-GIS) and the super-resolution through neighbor embedding, where the prior models are learned by employing the least-square methods, our framework aims to shape the prior model using sparse representation. Then this learned prior model is employed to guide the reconstruction process. Experiments show that our framework is very flexible, and achieves a competitive or even superior performance in terms of both reconstruction error and visual quality. Our method still exhibits an impressive ability to generate plausible HR facial images based on their sparse local structures.
URI: http://hdl.handle.net/10397/80065
ISSN: 0031-3203
EISSN: 1873-5142
DOI: 10.1016/j.patcog.2013.09.012
Rights: © 2013 The Authors. Published by ElsevierLtd. Open access under CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/3.0/)
The following publication Li, Y., Cai, C., Qiu, G., & Lam, K. -. (2014). Face hallucination based on sparse local-pixel structure. Pattern Recognition, 47(3), 1261-1270 is available at https://dx.doi.org/10.1016/j.patcog.2013.09.012
Appears in Collections:Journal/Magazine Article

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

SCOPUSTM   
Citations

37
Citations as of Jan 11, 2019

WEB OF SCIENCETM
Citations

28
Citations as of Jan 16, 2019

Google ScholarTM

Check

Altmetric


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