Text-independent writer identification and verification on offline Arabic handwriting

M.L. Bulacu; L.R.B. Schomaker; A.A Brink

Text-independent writer identification and verification on offline Arabic handwriting

M.L. Bulacu, L.R.B. Schomaker, A.A Brink

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

112 Citations (Scopus)

Abstract

In this paper we evaluate the performance on Arabic handwriting of the text-independent writer identification methods that we developed and tested on Western script in recent years. We use the IFN/ENIT data in the experiments reported here and our tests involve 350 writers. The results show that our methods are very, effective and the conclusions drawn in previous studies remain valid also on Arabic script. High performance is achieved by combining textural features (joint directional probability, distributions) with allographic features (grapheme-emission distributions).

Original language	English
Title of host publication	ICDAR 2007: NINTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS I AND II, PROCEEDINGS
Editors	B Werner
Place of Publication	LOS ALAMITOS
Publisher	IEEE (The Institute of Electrical and Electronics Engineers)
Pages	769-773
Number of pages	5
Volume	2
ISBN (Print)	978-0-7695-2822-9
Publication status	Published - 2007
Event	9th International Conference on Document Analysis and Recognition - , Brazil Duration: 23-Sept-2007 → 26-Sept-2007

Publication series

Name	IEEE Computer Society

Other

Other	9th International Conference on Document Analysis and Recognition
Country/Territory	Brazil
Period	23/09/2007 → 26/09/2007

Handle.net

Persistent link

Cite this

Bulacu, M. L., Schomaker, L. R. B., & Brink, A. A. (2007). Text-independent writer identification and verification on offline Arabic handwriting. In B. Werner (Ed.), ICDAR 2007: NINTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS I AND II, PROCEEDINGS (Vol. 2, pp. 769-773). (IEEE Computer Society). IEEE (The Institute of Electrical and Electronics Engineers).

Bulacu, M.L. ; Schomaker, L.R.B. ; Brink, A.A. / Text-independent writer identification and verification on offline Arabic handwriting. ICDAR 2007: NINTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS I AND II, PROCEEDINGS. editor / B Werner. Vol. 2 LOS ALAMITOS : IEEE (The Institute of Electrical and Electronics Engineers), 2007. pp. 769-773 (IEEE Computer Society).

@inproceedings{9ab4eefebf4141878dedeb2340225c9b,

title = "Text-independent writer identification and verification on offline Arabic handwriting",

abstract = "In this paper we evaluate the performance on Arabic handwriting of the text-independent writer identification methods that we developed and tested on Western script in recent years. We use the IFN/ENIT data in the experiments reported here and our tests involve 350 writers. The results show that our methods are very, effective and the conclusions drawn in previous studies remain valid also on Arabic script. High performance is achieved by combining textural features (joint directional probability, distributions) with allographic features (grapheme-emission distributions).",

author = "M.L. Bulacu and L.R.B. Schomaker and A.A Brink",

note = "Event: Proc. of 9th Int. Conf. on Document Analysis and Recognition (ICDAR 2007); 9th International Conference on Document Analysis and Recognition ; Conference date: 23-09-2007 Through 26-09-2007",

year = "2007",

language = "English",

isbn = "978-0-7695-2822-9",

volume = "2",

series = "IEEE Computer Society",

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

pages = "769--773",

editor = "B Werner",

booktitle = "ICDAR 2007: NINTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS I AND II, PROCEEDINGS",

}

Bulacu, ML, Schomaker, LRB & Brink, AA 2007, Text-independent writer identification and verification on offline Arabic handwriting. in B Werner (ed.), ICDAR 2007: NINTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS I AND II, PROCEEDINGS. vol. 2, IEEE Computer Society, IEEE (The Institute of Electrical and Electronics Engineers), LOS ALAMITOS, pp. 769-773, 9th International Conference on Document Analysis and Recognition, Brazil, 23/09/2007.

Text-independent writer identification and verification on offline Arabic handwriting. / Bulacu, M.L.; Schomaker, L.R.B.; Brink, A.A.
ICDAR 2007: NINTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS I AND II, PROCEEDINGS. ed. / B Werner. Vol. 2 LOS ALAMITOS: IEEE (The Institute of Electrical and Electronics Engineers), 2007. p. 769-773 (IEEE Computer Society).

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

TY - GEN

T1 - Text-independent writer identification and verification on offline Arabic handwriting

AU - Bulacu, M.L.

AU - Schomaker, L.R.B.

AU - Brink, A.A

N1 - Event: Proc. of 9th Int. Conf. on Document Analysis and Recognition (ICDAR 2007)

PY - 2007

Y1 - 2007

N2 - In this paper we evaluate the performance on Arabic handwriting of the text-independent writer identification methods that we developed and tested on Western script in recent years. We use the IFN/ENIT data in the experiments reported here and our tests involve 350 writers. The results show that our methods are very, effective and the conclusions drawn in previous studies remain valid also on Arabic script. High performance is achieved by combining textural features (joint directional probability, distributions) with allographic features (grapheme-emission distributions).

AB - In this paper we evaluate the performance on Arabic handwriting of the text-independent writer identification methods that we developed and tested on Western script in recent years. We use the IFN/ENIT data in the experiments reported here and our tests involve 350 writers. The results show that our methods are very, effective and the conclusions drawn in previous studies remain valid also on Arabic script. High performance is achieved by combining textural features (joint directional probability, distributions) with allographic features (grapheme-emission distributions).

M3 - Conference contribution

SN - 978-0-7695-2822-9

VL - 2

T3 - IEEE Computer Society

SP - 769

EP - 773

BT - ICDAR 2007: NINTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS I AND II, PROCEEDINGS

A2 - Werner, B

PB - IEEE (The Institute of Electrical and Electronics Engineers)

CY - LOS ALAMITOS

T2 - 9th International Conference on Document Analysis and Recognition

Y2 - 23 September 2007 through 26 September 2007

ER -

Bulacu ML, Schomaker LRB, Brink AA. Text-independent writer identification and verification on offline Arabic handwriting. In Werner B, editor, ICDAR 2007: NINTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS I AND II, PROCEEDINGS. Vol. 2. LOS ALAMITOS: IEEE (The Institute of Electrical and Electronics Engineers). 2007. p. 769-773. (IEEE Computer Society).

Text-independent writer identification and verification on offline Arabic handwriting

Abstract

Publication series

Other

Handle.net

Fingerprint

Cite this