Influence of fusion strategies on feature-based identification of low-resolution documents

Authors:
Ardhendu Behera;Denis Lalanne;Rolf Ingold
Affiliations:
University of Fribourg, Chemin du Musee 3, Switzerland;University of Fribourg, Chemin du Musee 3, Switzerland;University of Fribourg, Chemin du Musee 3, Switzerland
Venue:
Proceedings of the 2005 ACM symposium on Document engineering
Year:
2005

Citing 4
Cited 0

Document image database retrieval and browsing using texture analysis

ICDAR '97 Proceedings of the 4th International Conference on Document Analysis and Recognition
Indexing and retrieval of words in old documents

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Visual signature based identification of Low-resolution document images

Proceedings of the 2004 ACM symposium on Document engineering
Enhancement of Layout-based Identification of Low-resolution Documents using Geometrical Color Distribution

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition

Quantified Score

Hi-index	0.01

Visualization

Abstract

The paper describes a method by which one could use the documents captured from low-resolution handheld devices to retrieve the originals of those documents from a document store. The method considers conjunctively two complementary feature sets. First, the geometrical distribution of the color in the document's 2D image plane is preferred. Secondly, the shallow layout features is considered due to the poor resolution of the captured documents. We propose in this article to fuse those two complementary feature sets in order to improve document identification performance. Finally, in order to test the influence of merging strategies on document identification performance, a synergic method is proposed and evaluated relative to a similar method in which feature sets are simply considered sequentially.