A Laplacian Energy for Document Binarization

被引：74

作者：

Howe, Nicholas R. ^{[1
]}

机构：

[1] Smith Coll, Dept Comp Sci, Northampton, MA 01063 USA

来源：

11TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR 2011) | 2011年

关键词：

I.4.0.b Image processing software; I.4.6.b Graph-theoretic methods; I.4.6.d Pixel classification; FORM;

D O I：

10.1109/ICDAR.2011.11

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 algorithm for document binarization, building upon recent work in energy-based segmentation methods. It uses the Laplacian operator to assess the local likelihood of foreground and background labels, Canny edge detection to identify likely discontinuities, and a graph cut implementation to efficiently find the minimum energy solution of an objective function combining these concepts. The results of this algorithm place it near the top on both the DIBCO-09 and H-DIBCO assessments.

引用

页码：6 / 10

页数：5

共 16 条

[1] An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision [J].

Boykov, Y ;

Kolmogorov, V .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2004, 26 (09) :1124-1137

[2] A COMPUTATIONAL APPROACH TO EDGE-DETECTION [J].

CANNY, J .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1986, 8 (06) :679-698

[3]

Gatos Basilis, 2009, 2009 10th International Conference on Document Analysis and Recognition (ICDAR), P1375, DOI 10.1109/ICDAR.2009.246

[4] Efficient Binarization of Historical and Degraded Document Images [J].

Gatos, B. ;

Pratikakis, I. ;

Perantonis, S. J. .

PROCEEDINGS OF THE 8TH IAPR INTERNATIONAL WORKSHOP ON DOCUMENT ANALYSIS SYSTEMS, 2008, :447-454

[5] A comparison of binarization methods for historical archive documents [J].

He, J ;

Do, QDM ;

Downton, AC ;

Kim, JH .

EIGHTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS 1 AND 2, PROCEEDINGS, 2005, :538-542

[6]

Jie Wang, 2009, 2009 10th International Conference on Document Analysis and Recognition (ICDAR), P1176, DOI 10.1109/ICDAR.2009.126

[7]

Jung Gap Kuk, 2009, 2009 10th International Conference on Document Analysis and Recognition (ICDAR), P748, DOI 10.1109/ICDAR.2009.157

[8]

Kuk JG, 2008, IEEE IMAGE PROC, P2612, DOI 10.1109/ICIP.2008.4712329

[9] Convergence properties of the Nelder-Mead simplex method in low dimensions [J].

Lagarias, JC ;

Reeds, JA ;

Wright, MH ;

Wright, PE .

SIAM JOURNAL ON OPTIMIZATION, 1998, 9 (01) :112-147

[10] Binarization and cleanup of handwritten text from carbon copy medical form images [J].

Milewski, Robert ;

Govindaraju, Venu .

PATTERN RECOGNITION, 2008, 41 (04) :1308-1315

← 1 2 →