Tag-assisted sentence confabulation for intelligent text recognition

Fan Yang; Qinru Qiu; Morgan Bishop; Qing Wu

doi:10.1109/CISDA.2012.6291521

Tag-assisted sentence confabulation for intelligent text recognition

Fan Yang, Qinru Qiu, Morgan Bishop, Qing Wu

Department of Electrical Engineering & Computer Science

Research output: Contribution to conference › Paper › peer-review

4 Scopus citations

Abstract

Autonomous and intelligent recognition of printed or handwritten text image is one of the key features to achieve situational awareness. A neuromorphic model based intelligent text recognition (ITR) system has been developed in our previous work, which recognizes texts based on word level and sentence level context represented by statistical information of characters and words. While quite effective, sometimes the existing ITR system still generates results that are grammatically incorrect because it ignores semantic and syntactic properties of sentences. In this work, we improve the accuracy of the existing ITR system by incorporating parts-of-speech tagging into the text recognition procedure. Our experimental results show that the tag-assisted text recognition improves sentence level success rate by 33% in average.

Original language	English (US)
DOIs	https://doi.org/10.1109/CISDA.2012.6291521
State	Published - 2012
Event	2012 5th IEEE Symposium on Computational Intelligence for Security and Defence Applications, CISDA 2012 - Ottawa, ON, Canada Duration: Jul 11 2012 → Jul 13 2012

Other

Other	2012 5th IEEE Symposium on Computational Intelligence for Security and Defence Applications, CISDA 2012
Country/Territory	Canada
City	Ottawa, ON
Period	7/11/12 → 7/13/12

Keywords

cogent confabulation
parts-of-speech tagging
text recognition

ASJC Scopus subject areas

Artificial Intelligence
Computer Science Applications

Access to Document

10.1109/CISDA.2012.6291521

Cite this

@conference{8f316133e2554689bc4aaa8fa660acd5,

title = "Tag-assisted sentence confabulation for intelligent text recognition",

abstract = "Autonomous and intelligent recognition of printed or handwritten text image is one of the key features to achieve situational awareness. A neuromorphic model based intelligent text recognition (ITR) system has been developed in our previous work, which recognizes texts based on word level and sentence level context represented by statistical information of characters and words. While quite effective, sometimes the existing ITR system still generates results that are grammatically incorrect because it ignores semantic and syntactic properties of sentences. In this work, we improve the accuracy of the existing ITR system by incorporating parts-of-speech tagging into the text recognition procedure. Our experimental results show that the tag-assisted text recognition improves sentence level success rate by 33% in average.",

keywords = "cogent confabulation, parts-of-speech tagging, text recognition",

author = "Fan Yang and Qinru Qiu and Morgan Bishop and Qing Wu",

year = "2012",

doi = "10.1109/CISDA.2012.6291521",

language = "English (US)",

note = "2012 5th IEEE Symposium on Computational Intelligence for Security and Defence Applications, CISDA 2012 ; Conference date: 11-07-2012 Through 13-07-2012",

}

TY - CONF

T1 - Tag-assisted sentence confabulation for intelligent text recognition

AU - Yang, Fan

AU - Qiu, Qinru

AU - Bishop, Morgan

AU - Wu, Qing

PY - 2012

Y1 - 2012

N2 - Autonomous and intelligent recognition of printed or handwritten text image is one of the key features to achieve situational awareness. A neuromorphic model based intelligent text recognition (ITR) system has been developed in our previous work, which recognizes texts based on word level and sentence level context represented by statistical information of characters and words. While quite effective, sometimes the existing ITR system still generates results that are grammatically incorrect because it ignores semantic and syntactic properties of sentences. In this work, we improve the accuracy of the existing ITR system by incorporating parts-of-speech tagging into the text recognition procedure. Our experimental results show that the tag-assisted text recognition improves sentence level success rate by 33% in average.

AB - Autonomous and intelligent recognition of printed or handwritten text image is one of the key features to achieve situational awareness. A neuromorphic model based intelligent text recognition (ITR) system has been developed in our previous work, which recognizes texts based on word level and sentence level context represented by statistical information of characters and words. While quite effective, sometimes the existing ITR system still generates results that are grammatically incorrect because it ignores semantic and syntactic properties of sentences. In this work, we improve the accuracy of the existing ITR system by incorporating parts-of-speech tagging into the text recognition procedure. Our experimental results show that the tag-assisted text recognition improves sentence level success rate by 33% in average.

KW - cogent confabulation

KW - parts-of-speech tagging

KW - text recognition

UR - http://www.scopus.com/inward/record.url?scp=84867723209&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867723209&partnerID=8YFLogxK

U2 - 10.1109/CISDA.2012.6291521

DO - 10.1109/CISDA.2012.6291521

M3 - Paper

AN - SCOPUS:84867723209

T2 - 2012 5th IEEE Symposium on Computational Intelligence for Security and Defence Applications, CISDA 2012

Y2 - 11 July 2012 through 13 July 2012

ER -

Tag-assisted sentence confabulation for intelligent text recognition

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this