Label Consistent K-SVD: Learning a Discriminative Dictionary for Recognition

A label consistent K-SVD (LC-KSVD) algorithm to learn a discriminative dictionary for sparse coding is presented. In addition to using class labels of training data, we also associate label information with each dictionary item (columns of the dictionary matrix) to enforce discriminability in sparse...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on pattern analysis and machine intelligence Ročník 35; číslo 11; s. 2651 - 2664
Hlavní autoři:	Zhuolin Jiang, Zhe Lin, Davis, L. S.
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Los Alamitos, CA IEEE 01.11.2013 IEEE Computer Society
Témata:	Algorithm design and analysis Algorithms Applied sciences Artificial intelligence Biometry - methods Classification algorithms Coding, codes Computer science; control theory; systems Dictionaries Discriminant Analysis Discriminative dictionary learning discriminative sparse-code error Exact sciences and technology Face - anatomy & histology Humans Image Interpretation, Computer-Assisted - methods Image reconstruction incremental dictionary learning Information, signal and communications theory label consistent K-SVD Linear programming Pattern Recognition, Automated - methods Pattern recognition. Digital image processing. Computational geometry Signal and communications theory supervised learning Support Vector Machine Telecommunications and information theory Testing Training Computer vision Discriminant analysis Dictionaries Form defect Pattern recognition Object recognition incremental dictionary learning label consistent K-SVD Experimental result Image matching Supervised learning Scene analysis Optimal solution Sparse representation Discriminative dictionary learning Objective function discriminative sparse-code error Learning algorithm Artificial intelligence Multiple classification Singular value decomposition
ISSN:	0162-8828, 1939-3539, 2160-9292, 1939-3539
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!