VQ-Based Written Language Identification

Dat Tran; T Pham

doi:10.1109/ISSPA.2003.1224752

VQ-Based Written Language Identification

Dat Tran, T Pham

Information Systems

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

6 Citations (Scopus)

35 Downloads (Pure)

Abstract

Humans can recognize different types of written languages by their grammars and vocabularies. However, computers see everything as numbers. We present a computational algorithm for machine classification of written languages using the method of vector quantization. For a language document, each word is converted to a sequence of numbers and forms as a vector of numerical values according to its characters. This collection of vectors is then represented by a codebook that contains a number of template vectors for classification. The proposed method is more effective for machine learning than the n-gram based method, which has been widely used for written language identification. Experimental results of classifying a set of five closely roman-typed scripts show the promising application of the proposed method

Original language	English
Title of host publication	Proceedings of 2003 Seventh International Symposium on Signal Processing and Its Applications
Editors	K Abed-Meraim, I Bloch
Place of Publication	France
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	513-516
Number of pages	4
ISBN (Print)	0-7803-7947-0
DOIs	https://doi.org/10.1109/ISSPA.2003.1224752
Publication status	Published - 2003
Event	7th International Symposium on Signal Processing and Its Applications - , France Duration: 1 Jul 2003 → 4 Jul 2003

Conference

Conference	7th International Symposium on Signal Processing and Its Applications
Country/Territory	France
Period	1/07/03 → 4/07/03

Access to Document

10.1109/ISSPA.2003.1224752

PaperFinal published version, 242 KB

Cite this

@inproceedings{9b639261eaad4befb7b2b68c452448ca,

title = "VQ-Based Written Language Identification",

abstract = "Humans can recognize different types of written languages by their grammars and vocabularies. However, computers see everything as numbers. We present a computational algorithm for machine classification of written languages using the method of vector quantization. For a language document, each word is converted to a sequence of numbers and forms as a vector of numerical values according to its characters. This collection of vectors is then represented by a codebook that contains a number of template vectors for classification. The proposed method is more effective for machine learning than the n-gram based method, which has been widely used for written language identification. Experimental results of classifying a set of five closely roman-typed scripts show the promising application of the proposed method",

author = "Dat Tran and T Pham",

year = "2003",

doi = "10.1109/ISSPA.2003.1224752",

language = "English",

isbn = "0-7803-7947-0",

pages = "513--516",

editor = "K Abed-Meraim and I Bloch",

booktitle = "Proceedings of 2003 Seventh International Symposium on Signal Processing and Its Applications",

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

address = "United States",

note = "7th International Symposium on Signal Processing and Its Applications ; Conference date: 01-07-2003 Through 04-07-2003",

}

Tran, D & Pham, T 2003, VQ-Based Written Language Identification. in K Abed-Meraim & I Bloch (eds), Proceedings of 2003 Seventh International Symposium on Signal Processing and Its Applications. IEEE, Institute of Electrical and Electronics Engineers, France, pp. 513-516, 7th International Symposium on Signal Processing and Its Applications, France, 1/07/03. https://doi.org/10.1109/ISSPA.2003.1224752

VQ-Based Written Language Identification. / Tran, Dat; Pham, T.
Proceedings of 2003 Seventh International Symposium on Signal Processing and Its Applications. ed. / K Abed-Meraim; I Bloch. France: IEEE, Institute of Electrical and Electronics Engineers, 2003. p. 513-516.

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

TY - GEN

T1 - VQ-Based Written Language Identification

AU - Tran, Dat

AU - Pham, T

PY - 2003

Y1 - 2003

N2 - Humans can recognize different types of written languages by their grammars and vocabularies. However, computers see everything as numbers. We present a computational algorithm for machine classification of written languages using the method of vector quantization. For a language document, each word is converted to a sequence of numbers and forms as a vector of numerical values according to its characters. This collection of vectors is then represented by a codebook that contains a number of template vectors for classification. The proposed method is more effective for machine learning than the n-gram based method, which has been widely used for written language identification. Experimental results of classifying a set of five closely roman-typed scripts show the promising application of the proposed method

AB - Humans can recognize different types of written languages by their grammars and vocabularies. However, computers see everything as numbers. We present a computational algorithm for machine classification of written languages using the method of vector quantization. For a language document, each word is converted to a sequence of numbers and forms as a vector of numerical values according to its characters. This collection of vectors is then represented by a codebook that contains a number of template vectors for classification. The proposed method is more effective for machine learning than the n-gram based method, which has been widely used for written language identification. Experimental results of classifying a set of five closely roman-typed scripts show the promising application of the proposed method

U2 - 10.1109/ISSPA.2003.1224752

DO - 10.1109/ISSPA.2003.1224752

M3 - Conference contribution

SN - 0-7803-7947-0

SP - 513

EP - 516

BT - Proceedings of 2003 Seventh International Symposium on Signal Processing and Its Applications

A2 - Abed-Meraim, K

A2 - Bloch, I

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - France

T2 - 7th International Symposium on Signal Processing and Its Applications

Y2 - 1 July 2003 through 4 July 2003

ER -

VQ-Based Written Language Identification

Abstract

Conference

Access to Document

Fingerprint

Cite this