A Better Personalized Image Searching Algorithm

DOI

10.2991/mmebc-16.2016.463How to use a DOI?

Keywords

image; cluster algorithms; search engines; semantics; information fusion;

Abstract

Searching engines become the major tool for information retrieval of users with the rapidly increasing Web information. Traditional search engines can't completely evaluate users' search aims. It will lead to retrieval quality decline and increased cost. The paper proposed a better personalized image searching algorithm. It utilizes relevant feedback and SVM to build user interest model and return the personalized searching results to the users based on the muli-kernel cluster for images. The analysis of experiment results indicate that compared with the traditional searching algorithm the improved algorithm can enhance participation methods of users and solve the gap problem between low-level vision feature and high-level semantics. It can increase the mean recall and precision ratio to 8% and 10.5% compared with the traditional searching algorithm based on color. At the same time it can increase them to 13.2% and 28.56% respectively compared with the traditional one based on texture.

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  - He Huang
AU  - Guang feng Sheng
AU  - Jing jing Du
AU  - Xu Lei
AU  - Tao Zhang
PY  - 2016/06
DA  - 2016/06
TI  - A Better Personalized Image Searching Algorithm
BT  - Proceedings of the 2016 6th International Conference on Machinery, Materials, Environment, Biotechnology and Computer
PB  - Atlantis Press
SP  - 2301
EP  - 2305
SN  - 2352-5401
UR  - https://doi.org/10.2991/mmebc-16.2016.463
DO  - 10.2991/mmebc-16.2016.463
ID  - Huang2016/06
ER  -