Thangka Image Retrieval Method Based on Sub-block Dominant Color

DOI

10.2991/icmmcce-15.2015.106How to use a DOI?

Keywords

Image retrieval; Overlapped sub-block; Dominant color; Thangka image.

Abstract

In the light of the problem of lacking spatial knowledge of global color histogram and the characteristics of Thangka images, a method based on overlapping partition dominant color is presented. Translating color space from RGB to HSV, it designs overlapped sub-block to get the dominant color in each block. According overlapping partition model, the weight of every sub-block can be computed. Meanwhile, the reduced quadratic form distance method is applied to decrease arithmetic complexity. Similarity is calculated based on the dominant color feature of each partition. Experimental results show this approach is better than the method based on global dominant color; it can greatly reduce the dimension of color feature, and keep high retrieval precision simultaneity.

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  - Wanpin Gao
AU  - Wentao Shen
AU  - Weilan Wang
PY  - 2015/12
DA  - 2015/12
TI  - Thangka Image Retrieval Method Based on Sub-block Dominant Color
BT  - Proceedings of the 4th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering 2015
PB  - Atlantis Press
SP  - 525
EP  - 531
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmmcce-15.2015.106
DO  - 10.2991/icmmcce-15.2015.106
ID  - Gao2015/12
ER  -