Consolidating the results of automatic search in large scale digital collections

Abstract

We present a tool for grouping the results obtained from image-based document search engines. The obtained groups provide structure to the search engine’s output and allow immediate accessibility to the most prominent results. The tool is based on employing graphical Bayesian models and it reinforces retrieved items that are strongly linked to other retrievals. The utility of the tool is demonstrated within the context of visual search of documents from the Cairo Genizah.

2 Figures and Tables

Cite this paper

@inproceedings{Levy2012ConsolidatingTR, title={Consolidating the results of automatic search in large scale digital collections}, author={Noga Levy and Adiel Ben-Shalom and Itai Ben-Shalom and Lior Wolf and Nachum Dershowitz and Roni Shweka and Yaacov Choueka}, year={2012} }