Sciweavers

Share
GIS
2007
ACM

Comparing global and interest point descriptors for similarity retrieval in remote sensed imagery

10 years 2 months ago
Comparing global and interest point descriptors for similarity retrieval in remote sensed imagery
We investigate the application of a new category of low-level image descriptors termed interest points to remote sensed image analysis. In particular, we compare how scale and rotation invariant descriptors extracted from salient image locations perform compared to proven global texture features for similarity retrieval. Qualitative results using a geographic image retrieval application and quantitative results using an extensive ground truth dataset show that interest point descriptors support effective similarity retrieval in large collections of remote sensed imagery. Categories and Subject Descriptors H.3 [Information Storage and Retrieval]: Information Search and Retrieval General Terms Image retrieval Keywords Interest points, similarity search, remote sensed imagery
Shawn Newsam, Yang Yang
Added 09 Nov 2009
Updated 09 Nov 2009
Type Conference
Year 2007
Where GIS
Authors Shawn Newsam, Yang Yang
Comments (0)
books