Evolution of multiple states machines for recognition of online cursive handwriting

Ramin Halavati; Saeed Bagheri Shouraki; Saeed Hassanpour

doi:10.1109/WAC.2006.375750

Evolution of multiple states machines for recognition of online cursive handwriting

Ramin Halavati^*, Saeed Bagheri Shouraki, Saeed Hassanpour

^*Corresponding author for this work

Sharif University of Technology

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

1 Citation (Scopus)

Abstract

Recognition of cursive handwritings such as Persian script is a hard task as there is no fixed segmentation and simultaneous segmentation and recognition is required. This paper presents a novel comparison method for such tasks which is based on a Multiple States Machine to perform robust elastic comparison of small segments with high speed through generation and maintenance of a set of concurrent possible hypotheses, The approach is implemented on Persian (Farsi) language using a typical feature set and a specific tailored genetic algorithm and the recognition and computation time is compared with dynamic programming comparison approach. Copyright - World Automation Congress (WAC) 2006.

Original language	English
Title of host publication	2006 World Automation Congress, WAC'06
Publisher	IEEE Computer Society
ISBN (Print)	1889335339, 9781889335339
DOIs	https://doi.org/10.1109/WAC.2006.375750
Publication status	Published - 2006
Externally published	Yes
Event	2006 World Automation Congress, WAC'06 - Budapest, Hungary Duration: 24 Jun 2006 → 26 Jun 2006

Publication series

Name	2006 World Automation Congress, WAC'06

Conference

Conference	2006 World Automation Congress, WAC'06
Country/Territory	Hungary
City	Budapest
Period	24/06/06 → 26/06/06

Keywords

Elastic pattern matching
Evolutionary training
Online handwriting recognition

Access to Document

10.1109/WAC.2006.375750

Cite this

@inproceedings{bdd4dbccc3144d61a9b7af4f31fde4f6,

title = "Evolution of multiple states machines for recognition of online cursive handwriting",

abstract = "Recognition of cursive handwritings such as Persian script is a hard task as there is no fixed segmentation and simultaneous segmentation and recognition is required. This paper presents a novel comparison method for such tasks which is based on a Multiple States Machine to perform robust elastic comparison of small segments with high speed through generation and maintenance of a set of concurrent possible hypotheses, The approach is implemented on Persian (Farsi) language using a typical feature set and a specific tailored genetic algorithm and the recognition and computation time is compared with dynamic programming comparison approach. Copyright - World Automation Congress (WAC) 2006.",

keywords = "Elastic pattern matching, Evolutionary training, Online handwriting recognition",

author = "Ramin Halavati and Shouraki, {Saeed Bagheri} and Saeed Hassanpour",

year = "2006",

doi = "10.1109/WAC.2006.375750",

language = "English",

isbn = "1889335339",

series = "2006 World Automation Congress, WAC'06",

publisher = "IEEE Computer Society",

booktitle = "2006 World Automation Congress, WAC'06",

address = "United States",

note = "2006 World Automation Congress, WAC'06 ; Conference date: 24-06-2006 Through 26-06-2006",

}

Evolution of multiple states machines for recognition of online cursive handwriting. / Halavati, Ramin; Shouraki, Saeed Bagheri; Hassanpour, Saeed.
2006 World Automation Congress, WAC'06. IEEE Computer Society, 2006. 4259823 (2006 World Automation Congress, WAC'06).

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

TY - GEN

T1 - Evolution of multiple states machines for recognition of online cursive handwriting

AU - Halavati, Ramin

AU - Shouraki, Saeed Bagheri

AU - Hassanpour, Saeed

PY - 2006

Y1 - 2006

N2 - Recognition of cursive handwritings such as Persian script is a hard task as there is no fixed segmentation and simultaneous segmentation and recognition is required. This paper presents a novel comparison method for such tasks which is based on a Multiple States Machine to perform robust elastic comparison of small segments with high speed through generation and maintenance of a set of concurrent possible hypotheses, The approach is implemented on Persian (Farsi) language using a typical feature set and a specific tailored genetic algorithm and the recognition and computation time is compared with dynamic programming comparison approach. Copyright - World Automation Congress (WAC) 2006.

AB - Recognition of cursive handwritings such as Persian script is a hard task as there is no fixed segmentation and simultaneous segmentation and recognition is required. This paper presents a novel comparison method for such tasks which is based on a Multiple States Machine to perform robust elastic comparison of small segments with high speed through generation and maintenance of a set of concurrent possible hypotheses, The approach is implemented on Persian (Farsi) language using a typical feature set and a specific tailored genetic algorithm and the recognition and computation time is compared with dynamic programming comparison approach. Copyright - World Automation Congress (WAC) 2006.

KW - Elastic pattern matching

KW - Evolutionary training

KW - Online handwriting recognition

UR - http://www.scopus.com/inward/record.url?scp=36849044012&partnerID=8YFLogxK

U2 - 10.1109/WAC.2006.375750

DO - 10.1109/WAC.2006.375750

M3 - Conference contribution

AN - SCOPUS:36849044012

SN - 1889335339

SN - 9781889335339

T3 - 2006 World Automation Congress, WAC'06

BT - 2006 World Automation Congress, WAC'06

PB - IEEE Computer Society

T2 - 2006 World Automation Congress, WAC'06

Y2 - 24 June 2006 through 26 June 2006

ER -

Evolution of multiple states machines for recognition of online cursive handwriting

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this