Document layout extraction using soft ordering

Phillip E. Mitchell; Hong Yan

doi:10.1117/1.1512907

Document layout extraction using soft ordering

Phillip E. Mitchell, Hong Yan

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

2 Citations (Scopus)

Abstract

We present an algorithm that can determine the layout of an arbitrary document with great flexibility. The bottom-up approach of pattern extraction and classification provides good segmentation and is insensitive to skew. Soft ordering is a feature that improves segmentation by allowing distinct regions to physically overlap. It is also used to determine the correct order of the document regions. The algorithm can extract and place all the distinct document regions into a logical layout and column structure. © 2002 Society of Photo-Optical Instrumentation Engineers.

Original language	English
Pages (from-to)	2831-2843
Journal	Optical Engineering
Volume	41
Issue number	11
DOIs	https://doi.org/10.1117/1.1512907
Publication status	Published - Nov 2002

Research Keywords

Document layout analysis
Page segmentation
Pattern classification
Soft ordering

Access Output

10.1117/1.1512907

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{ed18f765aa704f32af21518d7ae15b38,

title = "Document layout extraction using soft ordering",

abstract = "We present an algorithm that can determine the layout of an arbitrary document with great flexibility. The bottom-up approach of pattern extraction and classification provides good segmentation and is insensitive to skew. Soft ordering is a feature that improves segmentation by allowing distinct regions to physically overlap. It is also used to determine the correct order of the document regions. The algorithm can extract and place all the distinct document regions into a logical layout and column structure. {\textcopyright} 2002 Society of Photo-Optical Instrumentation Engineers.",

keywords = "Document layout analysis, Page segmentation, Pattern classification, Soft ordering",

author = "Mitchell, {Phillip E.} and Hong Yan",

year = "2002",

month = nov,

doi = "10.1117/1.1512907",

language = "English",

volume = "41",

pages = "2831--2843",

journal = "Optical Engineering",

issn = "0091-3286",

publisher = "SPIE - International Society for Optical Engineering",

number = "11",

}

TY - JOUR

T1 - Document layout extraction using soft ordering

AU - Mitchell, Phillip E.

AU - Yan, Hong

PY - 2002/11

Y1 - 2002/11

N2 - We present an algorithm that can determine the layout of an arbitrary document with great flexibility. The bottom-up approach of pattern extraction and classification provides good segmentation and is insensitive to skew. Soft ordering is a feature that improves segmentation by allowing distinct regions to physically overlap. It is also used to determine the correct order of the document regions. The algorithm can extract and place all the distinct document regions into a logical layout and column structure. © 2002 Society of Photo-Optical Instrumentation Engineers.

AB - We present an algorithm that can determine the layout of an arbitrary document with great flexibility. The bottom-up approach of pattern extraction and classification provides good segmentation and is insensitive to skew. Soft ordering is a feature that improves segmentation by allowing distinct regions to physically overlap. It is also used to determine the correct order of the document regions. The algorithm can extract and place all the distinct document regions into a logical layout and column structure. © 2002 Society of Photo-Optical Instrumentation Engineers.

KW - Document layout analysis

KW - Page segmentation

KW - Pattern classification

KW - Soft ordering

UR - http://www.scopus.com/inward/record.url?scp=0036865152&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-0036865152&origin=recordpage

U2 - 10.1117/1.1512907

DO - 10.1117/1.1512907

M3 - RGC 21 - Publication in refereed journal

SN - 0091-3286

VL - 41

SP - 2831

EP - 2843

JO - Optical Engineering

JF - Optical Engineering

IS - 11

ER -

Document layout extraction using soft ordering

Abstract

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this