AN ALGORITHM FOR DICTIONARY GENERATION IN SPARSE REPRESENTATION

The K-COD （K-Complete Orthogonal Decomposition） algorithm for generating adaptive dictionary for signals sparse representation in the framework of K-means clustering is proposed in this paper, in which rank one approximation for components assembling signals based on COD and K-means clustering based...

Full description

Saved in:
Bibliographic Details
Published in:Journal of electronics (China) 2009-11, Vol.26 (6), p.836-841
Main Authors: Xie, Zongbo, Feng, Jiuchao
Format: Article
Language:English
Subjects:
Electrical Engineering
Engineering
化学需氧量
奇异值分解
正交分解
生成算法
稀疏表示
算法框架
自适应字典
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The K-COD （K-Complete Orthogonal Decomposition） algorithm for generating adaptive dictionary for signals sparse representation in the framework of K-means clustering is proposed in this paper, in which rank one approximation for components assembling signals based on COD and K-means clustering based on chaotic random search are well utilized. The results of synthetic test and empirical experiment for the real data show that the proposed algorithm outperforms recently reported alternatives： K-Singular Value Decomposition （K-SVD） algorithm and Method of Optimal Directions （MOD） algorithm.
ISSN:0217-9822
1993-0615
DOI:10.1007/s11767-008-0077-9