Research on Image Feature Extraction Method Based on Orthogonal Projection Transformation of Multi-task Learning Technology

DOI

10.2991/iccsee.2013.724How to use a DOI?

Keywords

multi-task learning, projection transformation, feature extraction, face recognition

Abstract

When the number of labeled training samples is very small, the sample information we can use would be very little. Because of this, the recognition rates of some traditional image recognition methods are not satisfactory. In order to use some related information that always exist in other databases, which is helpful to feature extraction and can improve the recognition rates, we apply multi-task learning to feature extraction of images. Our researches are based on transferring the projection transformation. Our experiments results on the public AR, FERET and CAS-PEAL databases demonstrate that the proposed approaches are more effective than the general related feature extraction methods in classification performance.

Copyright

© 2013, 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  - Xiaoyuan Jing
AU  - Li Li
AU  - Cailing Wang
AU  - Yongfang Yao
AU  - Fengnan Yu
PY  - 2013/03
DA  - 2013/03
TI  - Research on Image Feature Extraction Method Based on Orthogonal Projection Transformation of Multi-task Learning Technology
BT  - Proceedings of the 2nd International Conference on Computer Science and Electronics Engineering (ICCSEE 2013)
PB  - Atlantis Press
SP  - 2901
EP  - 2904
SN  - 1951-6851
UR  - https://doi.org/10.2991/iccsee.2013.724
DO  - 10.2991/iccsee.2013.724
ID  - Jing2013/03
ER  -