SYNTACTIC SEGMENTATION AND LABELING OF DIGITIZED PAGES FROM TECHNICAL JOURNALS

被引：77

作者：

KRISHNAMOORTHY, M

NAGY, G

SETH, S

VISWANATHAN, M

机构：

[1] IBM CORP,PENNANT SYST,BOULDER,CO 80301

[2] UNIV NEBRASKA,DEPT ELECT COMP & SYST ENGN,LINCOLN,NE 68588

来源：

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 1993年 / 15卷 / 07期

关键词：

Computational grammars - Pattern recognition - Program compilers - Trees (mathematics);

D O I：

10.1109/34.221173

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Alternating horizontal and vertical projection profiles are extracted from nested sub-blocks of scanned page images of technical documents. The thresholded profile strings are parsed using the compiler utilities Lex and Yacc. The significant document components are demarcated and identified by the recursive application of block grammars. Backtracking for error recovery and branch and bound for maximum-area labeling are implemented with Unix Shell programs. Results of the segmentation and labeling process are stored in a labeled X-Y tree. It is shown that families of technical documents that share the same layout conventions can be readily analyzed. More than 20 types of document entities can be identified in sample pages from the IBM Journal of Research and Development and IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. Potential applications include preprocessors for optical character recognition, document archival, and digital reprographics.

引用

页码：737 / 747

页数：11

共 32 条

[21]

NAGY G, 1986, PATTERN RECOGNITION, V2

[22]

NAGY G, 1991, 1ST P INT C DOC AN R, P141

[23]

NAGY G, 1988, DOCPROCS 98, P169, DOI DOI 10.1145/62506.62539

[24]

NARTKER TA, 1992, MAR P S DOC AN INF R

[25]

OGORMAN L, 1992, COMPUTER, V25

[26]

PAVLIDIS T, 1992, P IEEE, V80

[27]

Rice S. V., 1992, REPORT ACCURACY OCR

[28]

TANAKA E, 1992, MEMO GRADUATE SCH A, V10, P111

[29]

VISWANATHAN M, 1992, P SOC PHOTO-OPT INS, V1661, P6, DOI 10.1117/12.130269

[30]

VISWANATHAN M, 1990, THESIS RENSSELAER PO

← 1 2 3 4 →