A fast algorithm for bottom-up document layout analysis

被引：90

作者：

Simon, A

Pret, JC

Johnson, AP

机构：

[1] Institute for Computer Applications in Molecular Sciences, School of Chemistry, University of Leeds, Leeds

来源：

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 1997年 / 19卷 / 03期

关键词：

document analysis; physical page layout; bottom-up layout analysis; Kruskal's algorithm; spanning tree; chemical documents;

D O I：

10.1109/34.584106

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper describes a new bottom-up method for document layout analysis. The algorithm was implemented in the GLIDE (Chemical Literature Data Extraction) system (http://chem.leeds.ac.uk/ICAMS/CLiDE.html) but the method described here is suitable for a broader range of documents. It is based on Kruskal's algorithm and uses a special distance-metric between the components to construct the physical page structure. The method has all the major advantages of bottom-up systems: independence from different text spacing and independence from different block alignments. The algorithms computational complexity is reduced to linear by using heuristics and path-compression.

引用

页码：273 / 277

页数：5

共 14 条

[1]

Aho A. V., 1983, DATA STRUCTURES ALGO

[2] SEGMENTATION AND CLASSIFICATION OF MIXED TEXT/GRAPHICS/IMAGE DOCUMENTS [J].

FAN, KC ;

LIU, CH ;

WANG, YK .

PATTERN RECOGNITION LETTERS, 1994, 15 (12) :1201-1209

[3] CHEMICAL LITERATURE DATA EXTRACTION - THE CLIDE PROJECT [J].

IBISON, P ;

JACQUOT, M ;

KAM, F ;

NEVILLE, AG ;

SIMPSON, RW ;

TONNELIER, C ;

VENCZEL, T ;

JOHNSON, AP .

JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 1993, 33 (03) :338-344

[4]

IBISON P, 1992, P ONLINE INFORMATION

[5]

Ittner D. J., 1993, Proceedings of the Second International Conference on Document Analysis and Recognition (Cat. No.93TH0578-5), P336, DOI 10.1109/ICDAR.1993.395720

[6]

KAM F, 1992, P INT CHEM INF C ANN

[7] SYNTACTIC SEGMENTATION AND LABELING OF DIGITIZED PAGES FROM TECHNICAL JOURNALS [J].