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

Ardhendu Behera, Denis Lalanne, Rolf Ingold

Research output: Contribution to conferencePaper

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.
Original languageEnglish
Pages20-22
DOIs
Publication statusPublished - 2 Nov 2005
EventAssociation for Computing Machinery (ACM) Symposium on Document Engineering (DocEng) - Bristol, United Kingdom
Duration: 2 Nov 20054 Nov 2005

Conference

ConferenceAssociation for Computing Machinery (ACM) Symposium on Document Engineering (DocEng)
CountryUnited Kingdom
CityBristol
Period2/11/054/11/05

Fingerprint

Electric fuses
Merging
Fusion reactions
Color

Cite this

Behera, A., Lalanne, D., & Ingold, R. (2005). Influence of fusion strategies on feature-based identification of low-resolution documents. 20-22. Paper presented at Association for Computing Machinery (ACM) Symposium on Document Engineering (DocEng), Bristol, United Kingdom. https://doi.org/10.1145/1096601.1096607
Behera, Ardhendu ; Lalanne, Denis ; Ingold, Rolf. / Influence of fusion strategies on feature-based identification of low-resolution documents. Paper presented at Association for Computing Machinery (ACM) Symposium on Document Engineering (DocEng), Bristol, United Kingdom.
@conference{6651ee18cfc04c4483b8838361168bf6,
title = "Influence of fusion strategies on feature-based identification of low-resolution documents",
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.",
author = "Ardhendu Behera and Denis Lalanne and Rolf Ingold",
year = "2005",
month = "11",
day = "2",
doi = "10.1145/1096601.1096607",
language = "English",
pages = "20--22",
note = "Association for Computing Machinery (ACM) Symposium on Document Engineering (DocEng) ; Conference date: 02-11-2005 Through 04-11-2005",

}

Behera, A, Lalanne, D & Ingold, R 2005, 'Influence of fusion strategies on feature-based identification of low-resolution documents' Paper presented at Association for Computing Machinery (ACM) Symposium on Document Engineering (DocEng), Bristol, United Kingdom, 2/11/05 - 4/11/05, pp. 20-22. https://doi.org/10.1145/1096601.1096607

Influence of fusion strategies on feature-based identification of low-resolution documents. / Behera, Ardhendu; Lalanne, Denis; Ingold, Rolf.

2005. 20-22 Paper presented at Association for Computing Machinery (ACM) Symposium on Document Engineering (DocEng), Bristol, United Kingdom.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Influence of fusion strategies on feature-based identification of low-resolution documents

AU - Behera, Ardhendu

AU - Lalanne, Denis

AU - Ingold, Rolf

PY - 2005/11/2

Y1 - 2005/11/2

N2 - 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.

AB - 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.

UR - http://dl.acm.org/

UR - http://www.academia.edu/10123067/Influence_of_fusion_strategies_on_feature-based_identification_of_low-resolution_documents

U2 - 10.1145/1096601.1096607

DO - 10.1145/1096601.1096607

M3 - Paper

SP - 20

EP - 22

ER -

Behera A, Lalanne D, Ingold R. Influence of fusion strategies on feature-based identification of low-resolution documents. 2005. Paper presented at Association for Computing Machinery (ACM) Symposium on Document Engineering (DocEng), Bristol, United Kingdom. https://doi.org/10.1145/1096601.1096607