Orthogonal overcomplete kernel design for sparse representation

Yang, Z, Yang, Z, Qing, C, Ling, BW-K, Woo, WL and Sanei, S (2012) Orthogonal overcomplete kernel design for sparse representation Proceedings of the 2012 8th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2012.

	Text 2.pdf Restricted to Repository staff only Available under License : See the attached licence file. Download (650kB)
	Text (licence) SRI_deposit_agreement.pdf Restricted to Repository staff only Download (33kB)

Abstract

This paper proposes an optimal orthogonal overcomplete kernel design for sparse representation such that the sum of the L norms of a set of transformed vectors is minimized. When there is only one training vector in the set, both the optimal transformed vector and the optimal orthogonal kernel are derived analytically. When there is more than one training vector in the sets, this optimization problem is difficult to solve due to the orthogonal quadratic constraint. To address this difficulty, the paper proposes to convert the quadratic constrained optimization problem to an optimal rotational angle design problem. A set of vectors of rotational angles are initialized and the best converged vector of the rotational angles among the set is taken as the nearly globally optimal solution of the problem. Simulation results show that the proposed methodology is very effective and efficient. © 2012 IEEE.

Item Type:	Article
Divisions :	Surrey research (other units)
Authors :	Yang, Z, Yang, Z, Qing, C, Ling, BW-K, Woo, WL and Sanei, S
Date :	2012
DOI :	10.1109/CSNDSP.2012.6292723
Depositing User :	Symplectic Elements
Date Deposited :	28 Mar 2017 14:13
Last Modified :	24 Jan 2020 11:54
URI:	http://epubs.surrey.ac.uk/id/eprint/742472

Actions (login required)

View Item

Downloads