Construction of SVM Classifier for Image Retrieval

DOI

10.2991/emim-17.2017.219How to use a DOI?

Keywords

SVM classifier; K-means clustering algorithm; Optimal selection method; Image Retrieval

Abstract

In order to make the image retrieval more quickly and efficiently, this paper proposed a new method to construct SVM classifier, it uses K-means clustering algorithm to find the representative sample in the image database, which effectively reduces the searching range of the target image, and then the optimal sample is selected from the reduced sample set as the training sample by the optimal selection method. Finally we construct the optimal training sample set which is not only large in information and low in redundancy, so as to train a better SVM classifier to get higher retrieval efficiency. The experimental results show that compared with the traditional SVM-based image retrieval method, this method can greatly improve the retrieval performance.

Copyright

© 2017, 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  - Xuejing Ding
PY  - 2017/04
DA  - 2017/04
TI  - Construction of SVM Classifier for Image Retrieval
BT  - Proceedings of the 7th International Conference on Education, Management, Information and Mechanical Engineering (EMIM 2017)
PB  - Atlantis Press
SP  - 1090
EP  - 1093
SN  - 2352-538X
UR  - https://doi.org/10.2991/emim-17.2017.219
DO  - 10.2991/emim-17.2017.219
ID  - Ding2017/04
ER  -