A Distributed Algorithm for Content Based Indexing of Images by Projections on Ritz Primary Images
Data Mining and Knowledge Discovery
| Hi-index | 0.00 |
Ritz vectors approximate eigenvectors that are a common choice for primary images in content based indexing. They can be computed efficiently even when the images are accessed through slow communication such as the Internet. We develop an algorithm that computes Ritz vectors in one pass through the images. When iterated, the algorithm can recover the exact eigenvectors. In applications to image indexing and learning it may be necessary to compute primary images for indexing many sub-categories of the image set The proposed algorithm can compute these additional primary images "offline", without the image data much more costly even when access to the images is inexpensive.