A structured dictionary learning framework for sparse representation

DOI

10.2991/asei-15.2015.267How to use a DOI?

Keywords

sparse coding, face recognition, fisher criterion, spatial pooling, svm classifier.

Abstract

With the development of the computer, BOW model and SC model are applied to a large number of image classifications, and exhibit excellent performance, which become a hot topic in the field of computer vision. In the paper, we proposed a new framework of dictionary learning. the objective function based on sparse representation just consider the sparsity, while ignoring the spatial information of image and the correlation information of features, we apply spatial pyramid matching and add the discrimination fisher regularized penalty, by performing iterative optimization can get an excellent dictionary for representing image features, finally, we use max pooling and svm classifier for image classification. Experimental results in ORL and YALE face database show that the method has a high resolution.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yin Wei
PY  - 2015/05
DA  - 2015/05
TI  - A structured dictionary learning framework for sparse representation
BT  - Proceedings of the 2015 International conference on Applied Science and Engineering Innovation
PB  - Atlantis Press
SP  - 1352
EP  - 1356
SN  - 2352-5401
UR  - https://doi.org/10.2991/asei-15.2015.267
DO  - 10.2991/asei-15.2015.267
ID  - Wei2015/05
ER  -