A Constrained Algorithm Based NMFα for Image Representation
Joint Authors
Li, Tao
Ye, Mao
Bao, Jiao
Yang, Chenxue
Liu, Zijian
Source
Discrete Dynamics in Nature and Society
Issue
Vol. 2014, Issue 2014 (31 Dec. 2014), pp.1-12, 12 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2014-10-22
Country of Publication
Egypt
No. of Pages
12
Main Subjects
Abstract EN
Nonnegative matrix factorization (NMF) is a useful tool in learning a basic representation of image data.
However, its performance and applicability in real scenarios are limited because of the lack of image information.
In this paper, we propose a constrained matrix decomposition algorithm for image representation which contains parameters associated with the characteristics of image data sets.
Particularly, we impose label information as additional hard constraints to the α-divergence-NMF unsupervised learning algorithm.
The resulted algorithm is derived by using Karush-Kuhn-Tucker (KKT) conditions as well as the projected gradient and its monotonic local convergence is proved by using auxiliary functions.
In addition, we provide a method to select the parameters to our semisupervised matrix decomposition algorithm in the experiment.
Compared with the state-of-the-art approaches, our method with the parameters has the best classification accuracy on three image data sets.
American Psychological Association (APA)
Yang, Chenxue& Li, Tao& Ye, Mao& Liu, Zijian& Bao, Jiao. 2014. A Constrained Algorithm Based NMFα for Image Representation. Discrete Dynamics in Nature and Society،Vol. 2014, no. 2014, pp.1-12.
https://search.emarefa.net/detail/BIM-1035025
Modern Language Association (MLA)
Yang, Chenxue…[et al.]. A Constrained Algorithm Based NMFα for Image Representation. Discrete Dynamics in Nature and Society No. 2014 (2014), pp.1-12.
https://search.emarefa.net/detail/BIM-1035025
American Medical Association (AMA)
Yang, Chenxue& Li, Tao& Ye, Mao& Liu, Zijian& Bao, Jiao. A Constrained Algorithm Based NMFα for Image Representation. Discrete Dynamics in Nature and Society. 2014. Vol. 2014, no. 2014, pp.1-12.
https://search.emarefa.net/detail/BIM-1035025
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1035025