IEICE TRANSACTIONS on Information
Super-Resolution for Facial Images Based on Local Similarity Preserving
Summary :
To reconstruct low-resolution facial photographs which are in focus and without motion blur, a novel algorithm based on local similarity preserving is proposed. It is based on the theories of local manifold learning. The innovations of the new method include mixing point-based entropy and Euclidian distance to search for the nearest points, adding point-to-patch degradation model to restrict the linear weights and compensating the fusing patch to keep energy coherence. The compensation reduces the algorithm dependence on training sets and keeps the luminance of reconstruction constant. Experiments show that our method can effectively reconstruct 16
- Publication
- IEICE TRANSACTIONS on Information Vol.E95-D No.3 pp.892-896
- Publication Date
- 2012/03/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E95.D.892
- Type of Manuscript
- LETTER
- Category
- Image Processing and Video Processing
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Jin-Ping HE, Guang-Da SU, Jian-Sheng CHEN, "Super-Resolution for Facial Images Based on Local Similarity Preserving" in IEICE TRANSACTIONS on Information,
vol. E95-D, no. 3, pp. 892-896, March 2012, doi: 10.1587/transinf.E95.D.892.
Abstract: To reconstruct low-resolution facial photographs which are in focus and without motion blur, a novel algorithm based on local similarity preserving is proposed. It is based on the theories of local manifold learning. The innovations of the new method include mixing point-based entropy and Euclidian distance to search for the nearest points, adding point-to-patch degradation model to restrict the linear weights and compensating the fusing patch to keep energy coherence. The compensation reduces the algorithm dependence on training sets and keeps the luminance of reconstruction constant. Experiments show that our method can effectively reconstruct 16
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E95.D.892/_p
Copy
@ARTICLE{e95-d_3_892,
author={Jin-Ping HE, Guang-Da SU, Jian-Sheng CHEN, },
journal={IEICE TRANSACTIONS on Information},
title={Super-Resolution for Facial Images Based on Local Similarity Preserving},
year={2012},
volume={E95-D},
number={3},
pages={892-896},
abstract={To reconstruct low-resolution facial photographs which are in focus and without motion blur, a novel algorithm based on local similarity preserving is proposed. It is based on the theories of local manifold learning. The innovations of the new method include mixing point-based entropy and Euclidian distance to search for the nearest points, adding point-to-patch degradation model to restrict the linear weights and compensating the fusing patch to keep energy coherence. The compensation reduces the algorithm dependence on training sets and keeps the luminance of reconstruction constant. Experiments show that our method can effectively reconstruct 16
keywords={},
doi={10.1587/transinf.E95.D.892},
ISSN={1745-1361},
month={March},}
Copy
TY - JOUR
TI - Super-Resolution for Facial Images Based on Local Similarity Preserving
T2 - IEICE TRANSACTIONS on Information
SP - 892
EP - 896
AU - Jin-Ping HE
AU - Guang-Da SU
AU - Jian-Sheng CHEN
PY - 2012
DO - 10.1587/transinf.E95.D.892
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E95-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2012
AB - To reconstruct low-resolution facial photographs which are in focus and without motion blur, a novel algorithm based on local similarity preserving is proposed. It is based on the theories of local manifold learning. The innovations of the new method include mixing point-based entropy and Euclidian distance to search for the nearest points, adding point-to-patch degradation model to restrict the linear weights and compensating the fusing patch to keep energy coherence. The compensation reduces the algorithm dependence on training sets and keeps the luminance of reconstruction constant. Experiments show that our method can effectively reconstruct 16
ER -
English
