Text line extraction from multi-skewed handwritten documents

被引：78

作者：

Basu, S. ^{[1
]}

Chaudhuri, C. ^{[1
]}

Kundu, M. ^{[1
]}

Nasipuri, M. ^{[1
]}

Basu, D. K. ^{[1
]}

机构：

[1] Jadavpur Univ, Dept Comp Sci & Engn, Kolkata 700032, W Bengal, India

来源：

PATTERN RECOGNITION | 2007年 / 40卷 / 06期

关键词：

OCR; multi-skewed documents; text line extraction; connected component labelling; skew angle detection; touching line segmentation;

D O I：

10.1016/j.patcog.2006.10.002

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A novel text line extraction technique is presented for multi-skewed document images of handwritten English or Bengali text. It assumes that hypothetical water flows, front both left and right sides of the image frame, face obstruction from characters of text lines. The stripes of areas left unwetted on the image frame are finally labelled for extraction of text lines. The success rate of the technique, as observed experimentally, are 90.34% and 91.44% for handwritten Bengali and English document images, respectively. The work may contribute significantly for the development of applications related to optical character recognition of Bengali/English text. (c) 2006 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

引用

页码：1825 / 1839

页数：15

共 18 条

[1]

BASU S, 2003, P 5 INT C ADV PATT R, P271

[2] OFF-LINE CURSIVE SCRIPT WORD RECOGNITION [J].

BOZINOVIC, RM ;

SRIHARI, SN .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1989, 11 (01) :68-83

[3] Skew angle detection of digitized Indian script documents [J].

Chaudhuri, BB ;

Pal, U .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1997, 19 (02) :182-186

[4]

Gonzales Rafael C., 1992, DIGITAL IMAGE PROCES, P40

[5] Extracting curved text lines using local linearity of the text line [J].

Hideaki Goto ;

Hirotomo Aso .

International Journal on Document Analysis and Recognition, 1999, 2 (2-3) :111-119

[6]

Kise K., 1996, Proceedings of the 13th International Conference on Pattern Recognition, P788, DOI 10.1109/ICPR.1996.547276

[7]

LE DX, 1993, P SOC PHOTO-OPT INS, V1961, P251, DOI 10.1117/12.150957

[8] Chaincode contour processing for handwritten word recognition [J].

Madhvanath, S ;

Kim, G ;

Govindaraju, V .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1999, 21 (09) :928-932

[9] Text line segmentation in handwritten document using a production system [J].

Nicolas, S ;

Paquet, T ;

Heutte, L .

NINTH INTERNATIONAL WORKSHOP ON FRONTIERS IN HANDWRITING RECOGNITION, PROCEEDINGS, 2004, :245-250

[10]

Okun O., 1999, Proceedings of Fifth International Conference. PRIP '99. Pattern Recognition and Information Processing. Vol.1, P99

← 1 2 →