An Image Retrieval Method Based on PGH and Distance Histogram

DOI

10.2991/aiie-15.2015.133How to use a DOI?

Keywords

image retrieval; PGH; distance histogram

Abstract

An image retrieval method based on contour feature is proposed in this work. Pair-wise Geometric Histogram(PGH) captures the outer contour feature of the target shape. Distance histogram describes the interior details. Combining with two features, a twice retrieval strategy is proposed. Firstly, the query image and database images are compared with PGH. The eligible images are as candidates. Then, the secondary retrieval is carried out between the query image and candidate images. Images meeting the conditions are as the final result. Experiments show that the proposed method can resist rotation, translation transformation and scaling transformation, which has a good performance.

Copyright

© 2015, 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  - X. Zou
AU  - F.C. You
PY  - 2015/07
DA  - 2015/07
TI  - An Image Retrieval Method Based on PGH and Distance Histogram
BT  - Proceedings of the 2015 International Conference on Artificial Intelligence and Industrial Engineering
PB  - Atlantis Press
SP  - 493
EP  - 496
SN  - 1951-6851
UR  - https://doi.org/10.2991/aiie-15.2015.133
DO  - 10.2991/aiie-15.2015.133
ID  - Zou2015/07
ER  -