User Log Based Image Re-ranking and Retrieval

DOI

10.2991/iccasp-16.2017.92How to use a DOI?

Keywords

Text Based Image Retrieval, Re-ranking, Image Retrieval, Clustering, User Log.

Abstract

Digital world has developed tremendously. Initially textual information associated with images is used to do image based search. From user's perspective the final result contains both relevant as well irrelevant images. The expected yield from such a system is to get pertinent result. Satisfaction of the client will be enhanced if re-ranking is used as critical parameter. Images are displayed based on the category selected and re-ranked ac-cording to the query image opted by user. Image re-ranking based on user log technique is used to overcome the issues and to achieve efficient result. Expanding the keyword and clustering is done at offline mode which is al-so important parameters for the performance of the system. The performance of re-ranked image retrieval is improved with a reduction of time in seconds as compared to existing re-ranking method. The maintained user log helps to produce the relevant search results. The proposed user log system reduces the image retrieval and re-ranking duration from 17 seconds to 4 seconds.

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  - S. Sangeetha
AU  - S. Varma
PY  - 2016/12
DA  - 2016/12
TI  - User Log Based Image Re-ranking and Retrieval
BT  - Proceedings of the International Conference on Communication and Signal Processing 2016 (ICCASP 2016)
PB  - Atlantis Press
SP  - 640
EP  - 647
SN  - 1951-6851
UR  - https://doi.org/10.2991/iccasp-16.2017.92
DO  - 10.2991/iccasp-16.2017.92
ID  - Sangeetha2016/12
ER  -