Handwritten address recognition with open vocabulary using character n-grams

Anja Brakensiek; Jörg Rottland; Gerhard Rigoll

doi:10.1109/IWFHR.2002.1030936

Handwritten address recognition with open vocabulary using character n-grams

Anja Brakensiek, Jörg Rottland, Gerhard Rigoll

Chair of Human-Machine Communication

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

23 Scopus citations

Abstract

In this paper a recognition system, based on tied-mixture hidden Markov models, for handwritten address words is described, which makes use of a language model that consists of backoff character n-grams. For a dictionary-based recognition system it is essential that the structure of the address (name, street, city) is known. If the single parts of the address cannot be categorized, the used vocabulary is unknown and thus unlimited. The performance of this open vocabulary recognition using n-grams is compared to the use of dictionaries of different sizes. Especially, the confidence of recognition results and the possibility of a useful post-processing are significant advantages of language models.

Original language	English
Title of host publication	Proceedings - 8th International Workshop on Frontiers in Handwriting Recognition, IWFHR 2002
Pages	357-362
Number of pages	6
DOIs	https://doi.org/10.1109/IWFHR.2002.1030936
State	Published - 2002
Event	8th International Workshop on Frontiers in Handwriting Recognition, IWFHR 2002 - Ontario, ON, Canada Duration: 6 Aug 2002 → 8 Aug 2002

Publication series

Name	Proceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR
ISSN (Print)	1550-5235

Conference

Conference	8th International Workshop on Frontiers in Handwriting Recognition, IWFHR 2002
Country/Territory	Canada
City	Ontario, ON
Period	6/08/02 → 8/08/02

Access to Document

10.1109/IWFHR.2002.1030936

Cite this

Brakensiek, A., Rottland, J., & Rigoll, G. (2002). Handwritten address recognition with open vocabulary using character n-grams. In Proceedings - 8th International Workshop on Frontiers in Handwriting Recognition, IWFHR 2002 (pp. 357-362). Article 1030936 (Proceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR). https://doi.org/10.1109/IWFHR.2002.1030936

@inproceedings{55cb585755bd4bb68ea5f84f7b68360b,

title = "Handwritten address recognition with open vocabulary using character n-grams",

abstract = "In this paper a recognition system, based on tied-mixture hidden Markov models, for handwritten address words is described, which makes use of a language model that consists of backoff character n-grams. For a dictionary-based recognition system it is essential that the structure of the address (name, street, city) is known. If the single parts of the address cannot be categorized, the used vocabulary is unknown and thus unlimited. The performance of this open vocabulary recognition using n-grams is compared to the use of dictionaries of different sizes. Especially, the confidence of recognition results and the possibility of a useful post-processing are significant advantages of language models.",

author = "Anja Brakensiek and J{\"o}rg Rottland and Gerhard Rigoll",

year = "2002",

doi = "10.1109/IWFHR.2002.1030936",

language = "English",

isbn = "0769516920",

series = "Proceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR",

pages = "357--362",

booktitle = "Proceedings - 8th International Workshop on Frontiers in Handwriting Recognition, IWFHR 2002",

note = "8th International Workshop on Frontiers in Handwriting Recognition, IWFHR 2002 ; Conference date: 06-08-2002 Through 08-08-2002",

}

Brakensiek, A, Rottland, J & Rigoll, G 2002, Handwritten address recognition with open vocabulary using character n-grams. in Proceedings - 8th International Workshop on Frontiers in Handwriting Recognition, IWFHR 2002., 1030936, Proceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR, pp. 357-362, 8th International Workshop on Frontiers in Handwriting Recognition, IWFHR 2002, Ontario, ON, Canada, 6/08/02. https://doi.org/10.1109/IWFHR.2002.1030936

Handwritten address recognition with open vocabulary using character n-grams. / Brakensiek, Anja; Rottland, Jörg; Rigoll, Gerhard.
Proceedings - 8th International Workshop on Frontiers in Handwriting Recognition, IWFHR 2002. 2002. p. 357-362 1030936 (Proceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR).

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

TY - GEN

T1 - Handwritten address recognition with open vocabulary using character n-grams

AU - Brakensiek, Anja

AU - Rottland, Jörg

AU - Rigoll, Gerhard

PY - 2002

Y1 - 2002

N2 - In this paper a recognition system, based on tied-mixture hidden Markov models, for handwritten address words is described, which makes use of a language model that consists of backoff character n-grams. For a dictionary-based recognition system it is essential that the structure of the address (name, street, city) is known. If the single parts of the address cannot be categorized, the used vocabulary is unknown and thus unlimited. The performance of this open vocabulary recognition using n-grams is compared to the use of dictionaries of different sizes. Especially, the confidence of recognition results and the possibility of a useful post-processing are significant advantages of language models.

AB - In this paper a recognition system, based on tied-mixture hidden Markov models, for handwritten address words is described, which makes use of a language model that consists of backoff character n-grams. For a dictionary-based recognition system it is essential that the structure of the address (name, street, city) is known. If the single parts of the address cannot be categorized, the used vocabulary is unknown and thus unlimited. The performance of this open vocabulary recognition using n-grams is compared to the use of dictionaries of different sizes. Especially, the confidence of recognition results and the possibility of a useful post-processing are significant advantages of language models.

UR - http://www.scopus.com/inward/record.url?scp=18044383807&partnerID=8YFLogxK

U2 - 10.1109/IWFHR.2002.1030936

DO - 10.1109/IWFHR.2002.1030936

M3 - Conference contribution

AN - SCOPUS:18044383807

SN - 0769516920

SN - 9780769516929

T3 - Proceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR

SP - 357

EP - 362

BT - Proceedings - 8th International Workshop on Frontiers in Handwriting Recognition, IWFHR 2002

T2 - 8th International Workshop on Frontiers in Handwriting Recognition, IWFHR 2002

Y2 - 6 August 2002 through 8 August 2002

ER -

Handwritten address recognition with open vocabulary using character n-grams

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this