An Approach of Image Retrieval for Natural Scenes based on Local Features and Topology

DOI

10.2991/icmt-13.2013.112How to use a DOI?

Keywords

image retrieval; topology; local features.

Abstract

Image retrieval problem is a hotspot research filed in recent decades since it has a wide range of applications. Topology studies which used for image retrieval has rare research. This paper has characterized the departure from the image, fully tap the characteristics of the image itself, using image feature characteristics of local feature points to achieve the image content with regional dimensions. Marking the completion of the image content, the use of two images may be compared with similar characteristic sequence identification, signature sequence with the greatest similarity, which is considered to be similar. The approach which including topology theory can overcome the natural image retrieval at the local characteristics of defects, which can protect the global sequences, has a good characterization. Methods for the analysis of natural images operation, experimental results show that the combination of local feature topology method can overcome the mere use of local characteristics identified defects, to achieve the purpose of image retrieval.

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  - Yang Jun
PY  - 2013/11
DA  - 2013/11
TI  - An Approach of Image Retrieval for Natural Scenes based on Local Features and Topology
BT  - Proceedings of 3rd International Conference on Multimedia Technology(ICMT-13)
PB  - Atlantis Press
SP  - 903
EP  - 910
SN  - 1951-6851
UR  - https://doi.org/10.2991/icmt-13.2013.112
DO  - 10.2991/icmt-13.2013.112
ID  - Jun2013/11
ER  -