Face hallucination under an image decomposition perspective

In this paper we propose to convert the task of face hallucination into an image decomposition problem, and thenuse the morphological component analysis (MCA) for hallucinating a single face image, based on a novel three-stepframework. Firstly, a low-resolution input image is up-sampled by interpola...

Full description

Bibliographic Details
Main Authors: Liang, Yan, lai, Jian-huang, Xie, Xiaohua, Liu, Wan-quan
Other Authors: A. Salah
Format: Conference Paper
Published: Springer 2010
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/6113
_version_ 1848744983241162752
author Liang, Yan
lai, Jian-huang
Xie, Xiaohua
Liu, Wan-quan
author2 A. Salah
author_facet A. Salah
Liang, Yan
lai, Jian-huang
Xie, Xiaohua
Liu, Wan-quan
author_sort Liang, Yan
building Curtin Institutional Repository
collection Online Access
description In this paper we propose to convert the task of face hallucination into an image decomposition problem, and thenuse the morphological component analysis (MCA) for hallucinating a single face image, based on a novel three-stepframework. Firstly, a low-resolution input image is up-sampled by interpolation. Then, the MCA is employed to decompose the interpolated image into a high-resolution image and an unsharp masking, as MCA can properly decompose a signal into special parts according to typical dictionaries. Finally, a residue compensation, which is based on the neighbour reconstruction of patches, is performed to enhance the facial details. The proposed method can effectively exploit the facial properties for face hallucination under the image decomposition perspective. Experimental results demonstrate the effectiveness of our method, in terms of the visual quality of the hallucinated face images.
first_indexed 2025-11-14T06:10:08Z
format Conference Paper
id curtin-20.500.11937-6113
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T06:10:08Z
publishDate 2010
publisher Springer
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-61132022-12-09T07:12:35Z Face hallucination under an image decomposition perspective Liang, Yan lai, Jian-huang Xie, Xiaohua Liu, Wan-quan A. Salah T. Gevers N. Sebe A. Vinciarelli principal component analysis residue compensation face hallucination image decomposition morphological component analysis In this paper we propose to convert the task of face hallucination into an image decomposition problem, and thenuse the morphological component analysis (MCA) for hallucinating a single face image, based on a novel three-stepframework. Firstly, a low-resolution input image is up-sampled by interpolation. Then, the MCA is employed to decompose the interpolated image into a high-resolution image and an unsharp masking, as MCA can properly decompose a signal into special parts according to typical dictionaries. Finally, a residue compensation, which is based on the neighbour reconstruction of patches, is performed to enhance the facial details. The proposed method can effectively exploit the facial properties for face hallucination under the image decomposition perspective. Experimental results demonstrate the effectiveness of our method, in terms of the visual quality of the hallucinated face images. 2010 Conference Paper http://hdl.handle.net/20.500.11937/6113 Springer fulltext
spellingShingle principal component analysis
residue compensation
face hallucination
image decomposition
morphological component analysis
Liang, Yan
lai, Jian-huang
Xie, Xiaohua
Liu, Wan-quan
Face hallucination under an image decomposition perspective
title Face hallucination under an image decomposition perspective
title_full Face hallucination under an image decomposition perspective
title_fullStr Face hallucination under an image decomposition perspective
title_full_unstemmed Face hallucination under an image decomposition perspective
title_short Face hallucination under an image decomposition perspective
title_sort face hallucination under an image decomposition perspective
topic principal component analysis
residue compensation
face hallucination
image decomposition
morphological component analysis
url http://hdl.handle.net/20.500.11937/6113