.png){kind=icon}
Return
Symmetrical singular value decomposition representation for pattern recognition
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2016.05.075.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper proposes a novel and powerful pattern recognition method named symmetrical singular value decomposition representation (SSVDR) and presents its application to face recognition. The SSVDR method is based on singular value decomposition (SVD) and symmetry prior. In this method, the given image is firstly decomposed into a composition of a set of base images by the singular value decomposition technique. Then, the first few base images (which can be proved to be the low-frequency asymmetrical base images) are turned into symmetrical base images according to facial symmetry. Finally, a new representation of the original image is reestablished for the final recognition. For evaluating the performance of the SSVDR method, some experiments are conducted in two famous face databases: extended Yale B and CMU-PIE database. The experiment results show the proposed SSVDR method can reestablish a new homogeneous representation of the original image and has an encouraging performance on face recognition compared with the current state-of-the-art methods. (C) 2016 Elsevier B.V. All rights reserved.
Keywords:
Pattern recognition
Face recognition
Face representation
Singular value decomposition (SVD)
Symmetry prior
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W
Organization
Cited Papers
ShareSave
ShareSaveShareSaveShareSaveShadow compensation based on facial symmetry and image average for robust face recognition.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
ShareSaveShareSave
ShareSaveShareSave
View more