Abstract | ||
---|---|---|
This paper presents a strategy for content-based image retrieval. It is based on a meaningful segmentation procedure that can provide proper distributions for matching via the Earth mover's distance as a similarity metric. The segmentation procedure is based on a hierarchical watershed-driven algorithm that extracts automatically meaningful regions. In this framework, the proposed robust feature extraction plays a major role along with a novel region weighting for enhancing feature discrimination. Experimental results demonstrate the performance of the proposed strategy. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1007/1-4020-3443-1_19 | COMPUTATIONAL IMAGING AND VISION |
Keywords | Field | DocType |
content-based image retrieval,image segmentation,Earth Mover's distance,region weighting | Data mining,Weighting,Earth mover's distance,Computer science,Segmentation,Image retrieval,Watershed,Feature extraction,Image segmentation,Content-based image retrieval | Conference |
Volume | Citations | PageRank |
30 | 1 | 0.36 |
References | Authors | |
14 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
I. Pratikakis | 1 | 809 | 36.03 |
Iris Vanhamel | 2 | 100 | 9.96 |
H. Sahli | 3 | 40 | 4.16 |
B. Gatos | 4 | 900 | 49.03 |
S. Perantonis | 5 | 122 | 3.58 |