From Contours to Characters Segmentation of Cursive Handwritten Words with Neural Assistance

被引：0

作者：

Kurniawan, Fajri ^{[1
]}

Rehman, Amjad ^{[1
]}

Mohamad, Dzulkifli ^{[1
]}

机构：

[1] Univ Teknol Malaysia, Dept Comp Graph & Multimedia, Skudai Johor, Malaysia

来源：

ICICI-BME: 2009 INTERNATIONAL CONFERENCE ON INSTRUMENTATION, COMMUNICATION, INFORMATION TECHNOLOGY, AND BIOMEDICAL ENGINEERING | 2009年

关键词：

character segmentation; contour analysis; neural network; cursive handwritten; off-line handwriting; RECOGNITION;

D O I：

暂无

中图分类号：

R318 [生物医学工程];

学科分类号：

0831 ;

摘要：

This paper presents a novel algorithm to resolve an open problem to correctly locating letter boundaries in off-line unconstrained cursive handwritten word images. The proposed algorithm is based on vertical contour analysis. Following preprocessing, during the course of pre-segmentation vertical contours are analyzed from right to left. Furthermore to improve accuracy of segmentation, trained ANN is employed to validate segment points. For fair analysis, experiments were performed on JAM benchmark database. Results obtained thus show that the proposed approach is capable to accurately locating the letter boundaries for unconstraint cursive handwritten words.

引用

页码：153 / 156

页数：4

共 25 条

[1] Blumenstein M, 2004, IEEE IJCNN, P2983
[2] Analysis of segmentation performance on the CEDAR benchmark database
Blumenstein, M
Verma, B
[J]. SIXTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, PROCEEDINGS, 2001, : 1142 - 1146
[3] Blumenstein M., 1999, Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR '99 (Cat. No.PR00318), P281, DOI 10.1109/ICDAR.1999.791779
[4] Blumenstein M, 1999, P INT JOINT C NEUR N, V4, P878
[5] BORTOLOZZI F, 2005, DOCUMENT ANAL, P1
[6] OFF-LINE CURSIVE SCRIPT WORD RECOGNITION
BOZINOVIC, RM
SRIHARI, SN
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1989, 11 (01) : 68 - 83
[7] Cheng CK, 2005, PROC INT CONF DOC, P650
[8] Cheng CK, 2005, P 4 AS PAC INT S INF, P56
[9] Cheng CK, 2004, 5 INT C SIM EV LEARN
[10] EASTWOOD B, 1997, INT C COMP INT MULT, P286

← 1 2 3 →