Three-stage Handwriting Stroke Extraction Method with Hidden Loop Recovery

Vladimir Pervouchine; Graham Leedham; Melikhov Konstantin

doi:10.1109/ICDAR.2005.241

Three-stage Handwriting Stroke Extraction Method with Hidden Loop Recovery

Vladimir Pervouchine
, Graham Leedham
, Melikhov Konstantin

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

10 Citations (Scopus)

Abstract

A method for extraction of strokes from handwriting characters and graphemes is presented. The method allows the modelling of the original pen tip trajectory close to that perceived by humans, thus allowing its use in writer identification and verification tasks. The method is also capable of identifying retraced strokes and recovering hidden loops. Strokes are represented as cubic splines. The method extracts strokes in three stages: vectorisation, merging of skeletal branches and loop recovery, and final adjustment of near-junction and loop pieces. The evaluation of the method is performed by using its results for structural feature extraction and writer classification based on the features.

Original language	English
Title of host publication	Proceedings of the 2005 Eight International Conference on Document Analysis and Recognition (ICDAR'05)
Place of Publication	Los Alamitos, United States of America
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	307-311
Volume	1
ISBN (Print)	0769524206
DOIs	https://doi.org/10.1109/ICDAR.2005.241
Publication status	Published - 2005
Event	ICDAR 2005: 8th International Conference on Document Analysis and Recognition - Seoul, South Korea Duration: 29 Aug 2005 → 1 Sept 2005

Conference

Conference	ICDAR 2005: 8th International Conference on Document Analysis and Recognition
City	Seoul, South Korea
Period	29/08/05 → 1/09/05

Keywords

Pattern Recognition and Data Mining
Image Processing
Artificial Intelligence and Image Processing

Access to Document

10.1109/ICDAR.2005.241

https://hdl.handle.net/1959.11/6664

Handle.net

Persistent link

Cite this

@inproceedings{567f91c8df09416fa19864d2aa46b864,

title = "Three-stage Handwriting Stroke Extraction Method with Hidden Loop Recovery",

abstract = "A method for extraction of strokes from handwriting characters and graphemes is presented. The method allows the modelling of the original pen tip trajectory close to that perceived by humans, thus allowing its use in writer identification and verification tasks. The method is also capable of identifying retraced strokes and recovering hidden loops. Strokes are represented as cubic splines. The method extracts strokes in three stages: vectorisation, merging of skeletal branches and loop recovery, and final adjustment of near-junction and loop pieces. The evaluation of the method is performed by using its results for structural feature extraction and writer classification based on the features.",

keywords = "Pattern Recognition and Data Mining, Image Processing, Artificial Intelligence and Image Processing",

author = "Vladimir Pervouchine and Graham Leedham and Melikhov Konstantin",

year = "2005",

doi = "10.1109/ICDAR.2005.241",

language = "English",

isbn = "0769524206",

volume = "1",

pages = "307--311",

booktitle = "Proceedings of the 2005 Eight International Conference on Document Analysis and Recognition (ICDAR'05)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

note = "ICDAR 2005: 8th International Conference on Document Analysis and Recognition ; Conference date: 29-08-2005 Through 01-09-2005",

}

Pervouchine, V, Leedham, G & Konstantin, M 2005, Three-stage Handwriting Stroke Extraction Method with Hidden Loop Recovery. in Proceedings of the 2005 Eight International Conference on Document Analysis and Recognition (ICDAR'05). vol. 1, Institute of Electrical and Electronics Engineers (IEEE), Los Alamitos, United States of America, pp. 307-311, ICDAR 2005: 8th International Conference on Document Analysis and Recognition, Seoul, South Korea, 29/08/05. https://doi.org/10.1109/ICDAR.2005.241

Three-stage Handwriting Stroke Extraction Method with Hidden Loop Recovery. / Pervouchine, Vladimir; Leedham, Graham; Konstantin, Melikhov.
Proceedings of the 2005 Eight International Conference on Document Analysis and Recognition (ICDAR'05). Vol. 1 Los Alamitos, United States of America: Institute of Electrical and Electronics Engineers (IEEE), 2005. p. 307-311.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Three-stage Handwriting Stroke Extraction Method with Hidden Loop Recovery

AU - Pervouchine, Vladimir

AU - Leedham, Graham

AU - Konstantin, Melikhov

PY - 2005

Y1 - 2005

N2 - A method for extraction of strokes from handwriting characters and graphemes is presented. The method allows the modelling of the original pen tip trajectory close to that perceived by humans, thus allowing its use in writer identification and verification tasks. The method is also capable of identifying retraced strokes and recovering hidden loops. Strokes are represented as cubic splines. The method extracts strokes in three stages: vectorisation, merging of skeletal branches and loop recovery, and final adjustment of near-junction and loop pieces. The evaluation of the method is performed by using its results for structural feature extraction and writer classification based on the features.

AB - A method for extraction of strokes from handwriting characters and graphemes is presented. The method allows the modelling of the original pen tip trajectory close to that perceived by humans, thus allowing its use in writer identification and verification tasks. The method is also capable of identifying retraced strokes and recovering hidden loops. Strokes are represented as cubic splines. The method extracts strokes in three stages: vectorisation, merging of skeletal branches and loop recovery, and final adjustment of near-junction and loop pieces. The evaluation of the method is performed by using its results for structural feature extraction and writer classification based on the features.

KW - Pattern Recognition and Data Mining

KW - Image Processing

KW - Artificial Intelligence and Image Processing

UR - http://www3.ntu.edu.sg/SCE/labs/forse/PDF/docExam_11.pdf

U2 - 10.1109/ICDAR.2005.241

DO - 10.1109/ICDAR.2005.241

M3 - Conference contribution

SN - 0769524206

VL - 1

SP - 307

EP - 311

BT - Proceedings of the 2005 Eight International Conference on Document Analysis and Recognition (ICDAR'05)

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Los Alamitos, United States of America

T2 - ICDAR 2005: 8th International Conference on Document Analysis and Recognition

Y2 - 29 August 2005 through 1 September 2005

ER -

Pervouchine V, Leedham G, Konstantin M. Three-stage Handwriting Stroke Extraction Method with Hidden Loop Recovery. In Proceedings of the 2005 Eight International Conference on Document Analysis and Recognition (ICDAR'05). Vol. 1. Los Alamitos, United States of America: Institute of Electrical and Electronics Engineers (IEEE). 2005. p. 307-311 doi: 10.1109/ICDAR.2005.241

Three-stage Handwriting Stroke Extraction Method with Hidden Loop Recovery

Abstract

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Cite this