Multi-scale indices for content-based image retrieval (1999) [1 citations — 1 self]
|
Abstract:
Abstract-- For automatc remote-sensing image interpretation it is important to give specific consideration to the resolution of the data. The performance of content-based retrieval systems can be enhanced significantly if the scale of spatial features is used explicitly as a meta feature. This allows to use lowdimensional feature vectors at each scale instead of a highdimensional feature vector for all scales. We developed a system where the user can query for signal properties, like texture characteristics. He is encouraged to restrict the search space by indicating the scale he is interested in. The signal oriented search is done using indices that are computed completely unsupervised. These indices represent the characteristic signal classes of the data. The system does no interpretation of the classes. It is up to the user to "name " the contents according to his application interest.
Citations
| 484 | Textural features for image classification – Haralick, Shanmugam, et al. - 1973 |
| 14 | Spatial information retrieval from remote sensing images: B. Gibbs Markov random fields – Schroder, Rehrauer, et al. - 1998 |
| 9 | Adhemar Bultheel. Wavelet transforms using lifting scheme – Uytterhoeven, Roose - 1997 |
| 6 | Gool. Advanced remote sensing information system at ETH Zurich and DLR – Seidel, Datcu, et al. - 1999 |
| 4 | Interactive learning in remote sensing image databases – Schroder - 1999 |
| 3 | Advanced query and retrieval techniques for remote sensing image databases – Seidel, Therre, et al. - 1998 |
| 2 | Bayesian modeling of remote-sensing image content – Schroder, Seidel, et al. - 1999 |
