Data Field-based Support Vector Machine for Image Classification

DOI

10.2991/icmemtc-16.2016.220How to use a DOI?

Keywords

Image Classification; Data field; topological Potential; Diffusion distance; SVM

Abstract

In computer vision, object recognition is still a challenge. In this paper, a new method based on data field is proposed for image object classification with color histograms and diffusion distances. Among them, the topological potential is used to select the optimal parameters. The experimental results show that the proposed method has better accuracy and shorter run time than four common kernels. It not only overcomes the drawbacks of the existing parameter selection method, but also coincident with Vapnik's theory, which theoretically guarantees the generalization of learning machines.

Copyright

© 2016, 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  - Yi Lin
PY  - 2016/04
DA  - 2016/04
TI  - Data Field-based Support Vector Machine for Image Classification
BT  - Proceedings of the 2016 3rd International Conference on Materials Engineering, Manufacturing Technology and Control
PB  - Atlantis Press
SP  - 1112
EP  - 1116
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmemtc-16.2016.220
DO  - 10.2991/icmemtc-16.2016.220
ID  - Lin2016/04
ER  -