DocumentCode :
73290
Title :
Local Coordinate Concept Factorization for Image Representation
Author :
Haifeng Liu ; Zheng Yang ; Ji Yang ; Zhaohui Wu ; Xuelong Li
Author_Institution :
Coll. of Comput. Sci., Zhejiang Univ., Hangzhou, China
Volume :
25
Issue :
6
fYear :
2014
fDate :
Jun-14
Firstpage :
1071
Lastpage :
1082
Abstract :
Learning sparse representation of high-dimensional data is a state-of-the-art method for modeling data. Matrix factorization-based techniques, such as nonnegative matrix factorization and concept factorization (CF), have shown great advantages in this area, especially useful for image representation. Both of them are linear learning problems and lead to a sparse representation of the images. However, the sparsity obtained by these methods does not always satisfy locality conditions. For example, the learned new basis vectors may be relatively far away from the original data. Thus, we may not be able to achieve the optimal performance when using the new representation for other learning tasks, such as classification and clustering. In this paper, we introduce a locality constraint into the traditional CF. By requiring the concepts (basis vectors) to be as close to the original data points as possible, each datum can be represented by a linear combination of only a few basis concepts. Thus, our method is able to achieve sparsity and locality simultaneously. We analyze the complexity of our novel algorithm and demonstrate the effectiveness in comparison with the state-of-the-art approaches through a set of evaluations based on realworld applications.
Keywords :
image classification; image representation; iterative methods; learning (artificial intelligence); matrix decomposition; pattern clustering; sparse matrices; CF; basis vectors; data modeling; data points; datum representation; high-dimensional data; image classification; image clustering; learning tasks; linear learning problems; local coordinate concept factorization; locality conditions; locality constraint; matrix factorization-based techniques; nonnegative matrix factorization; optimal performance; sparse image representation; sparse representation learning; sparsity condition; Algorithm design and analysis; Approximation methods; Data models; Encoding; Linear programming; Sparse matrices; Vectors; Data representation; dimensionality reduction; image clustering; matrix factorization; matrix factorization.;
fLanguage :
English
Journal_Title :
Neural Networks and Learning Systems, IEEE Transactions on
Publisher :
ieee
ISSN :
2162-237X
Type :
jour
DOI :
10.1109/TNNLS.2013.2286093
Filename :
6650088
Link To Document :
بازگشت