On-Line Handwritten Character Recognition using Kohonen Networks

被引：0

作者：

Sreeraj, M. ^{[1
]}

Idicula, Sumam Mary ^{[1
]}

机构：

[1] Cochin Univ Sci & Technol, Dept Comp Sci, Cochin 682016, Kerala, India

来源：

2009 WORLD CONGRESS ON NATURE & BIOLOGICALLY INSPIRED COMPUTING (NABIC 2009) | 2009年

关键词：

Malayalam handwritten characters; Artificial Neural Network; Feature extraction; Kohonen network (SOM);

D O I：

暂无

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 presents an efficient Online Handwritten character Recognition System for Malayalam Characters (OHR-M) using Kohonen network It would help in recognizing Malayalam text entered using pen-like devices. It will be more natural and efficient way for users to enter text using a pen than keyboard and mouse. To identify the difference between similar characters in Malayalam a novel feature extraction method has been adopted-a combination of context bitmap and normalized (x, y) coordinates. The system reported an accuracy of 88.75% which is writer independent with a recognition time of 15-32 milliseconds.

引用

页码：1424 / 1429

页数：6

共 11 条

[1]

[Anonymous], 1979, NOBUYUKI OTSU

[2]

BALAJI R, 2006, 10 INT WORKSH FRONT

[3]

GUYON I, 1994, INT C PATT REC ICPR

[4] Online handwriting recognition: The NPen++ recognizer [J].

Jaeger S. ;

Manke S. ;

Reichert J. ;

Waibel A. .

International Journal on Document Analysis and Recognition, 2001, Springer Verlag (03) :169-180

[5]

MANKE S, 1994, INT C PATT RECOG, P596, DOI 10.1109/ICPR.1994.577051

[6]

MEZGHANI N, P 8 INT WORKSH FRONT

[7] On-line and off-line handwriting recognition: A comprehensive survey [J].

Plamondon, R ;

Srihari, SN .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2000, 22 (01) :63-84

[8]

RAJU G, 2006, P 14 INT C ADV COMP, P217

[9]

ROSHINI VS, 2005, P INT C COGN REC, P477

[10]

Verma B, 2004, IEEE IJCNN, P1337

← 1 2 →