A New Algorithm for Detecting Text Line in Handwritten Documents

Yi Li; Yefeng Zheng; David Doermann; Stefan Jaeger

inria-00108340, version 1

A New Algorithm for Detecting Text Line in Handwritten Documents

Yi Li () ¹, Yefeng Zheng () ², David Doermann () ¹, Stefan Jaeger () ¹

Tenth International Workshop on Frontiers in Handwriting Recognition (2006)

Abstract: Curvilinear text line detection and segmentation in handwritten documents is a significant challenge for handwriting recognition. Given no prior knowledge of script, we model text line detection as an image segmentation problem by enhancing text line structure using a Gaussian window, and adopting the level set method to evolve text line boundaries. Experiments show that the proposed method achieves high accuracy for detecting text lines in both handwritten and machine printed documents with many scripts.

1: Laboratory for Language and Media Processing (LAMP)
University of Maryland at College Park
2: Siemens Corporate Research
Siemens

inria-00108340, version 1
http://hal.inria.fr/inria-00108340
oai:hal.inria.fr:inria-00108340
From: Ist Rennes <>
Submitted on: Friday, 20 October 2006 14:54:15
Updated on: Friday, 20 October 2006 15:39:15

See detailed view

Associated documents

PDF :

Export

Bibtex EndNote TEI RefWorks

<?xml version="1.0" encoding="UTF-8"?>
<listBibl xmlns="http://www.tei-c.org/ns/1.0" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML">
<listBibl type="inproceedings"><head>Peer-reviewed conferences/proceedings</head>
<biblStruct type="inproceedings" xml:id="inria-00108340"><analytic>
<author><persName><forename>Yi</forename><surname>Li</surname></persName>
<affiliation>
<orgName type="laboratory">LAMP</orgName>
<orgName type="team">Laboratory for Language and Media Processing</orgName>
<country>US</country>
<orgName type="institution">University of Maryland at College Park</orgName>
</affiliation>
</author>
<author><persName><forename>Yefeng</forename><surname>Zheng</surname></persName>
<affiliation>
<orgName type="team">Siemens Corporate Research</orgName>
<country>US</country>
<orgName type="institution">Siemens</orgName>
</affiliation>
</author>
<author><persName><forename>David</forename><surname>Doermann</surname></persName>
<affiliation>
<orgName type="laboratory">LAMP</orgName>
<orgName type="team">Laboratory for Language and Media Processing</orgName>
<country>US</country>
<orgName type="institution">University of Maryland at College Park</orgName>
</affiliation>
</author>
<author><persName><forename>Stefan</forename><surname>Jaeger</surname></persName>
<affiliation>
<orgName type="laboratory">LAMP</orgName>
<orgName type="team">Laboratory for Language and Media Processing</orgName>
<country>US</country>
<orgName type="institution">University of Maryland at College Park</orgName>
</affiliation>
</author>
<title type="main" level="a">A New Algorithm for Detecting Text Line in Handwritten Documents</title></analytic><monogr><meeting>Tenth International Workshop on Frontiers in Handwriting Recognition</meeting><imprint><publisher>Suvisoft</publisher><pubPlace><settlement>La Baule (France)</settlement></pubPlace><biblScope type="publicationDate">2006-10-23</biblScope></imprint></monogr><idno type="HALid">http://hal.inria.fr/inria-00108340</idno><idno type="HALFile">http://hal.inria.fr/inria-00108340/PDF/cr1093170512534.pdf</idno></biblStruct>
</listBibl>
</listBibl>