A Novel HMM Decoding Algorithm Permitting Long-Term Dependencies and Its Application to Handwritten Word Recognition

Volkmar Frinken; Ryosuke Kakisako; Seiichi Uchida

doi:10.1109/ICFHR.2014.29

A Novel HMM Decoding Algorithm Permitting Long-Term Dependencies and Its Application to Handwritten Word Recognition

Volkmar Frinken, Ryosuke Kakisako, Seiichi Uchida

実世界ロボティクス

研究成果: 書籍/レポートタイプへの寄稿 › 会議への寄与

1 被引用数 (Scopus)

抄録

A new decoding for hidden Markov models is presented. As opposed to the commonly used Viterbi algorithm, it is based on the Min-Cut/Max-Flow algorithm instead of dynamic programming. Therefore non-Markovian long-term dependencies can easily be added to influence the decoding path while still finding the optimal decoding in polynomial time. We demonstrate through an experimental evaluation how these constraints can be used to improve an HMM-based handwritten word recognition system that model words via linear character-HMM by restricting the length of each character.

本文言語	英語
ホスト出版物のタイトル	Proceedings - 14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014
出版社	Institute of Electrical and Electronics Engineers Inc.
ページ	128-133
ページ数	6
ISBN（電子版）	9781479943340
DOI	https://doi.org/10.1109/ICFHR.2014.29
出版ステータス	出版済み - 12月 9 2014
イベント	14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014 - Hersonissos, Crete Island, ギリシャ継続期間: 9月 1 2014 → 9月 4 2014

出版物シリーズ

名前	Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR
巻	2014-December
ISSN（印刷版）	2167-6445
ISSN（電子版）	2167-6453

その他

その他	14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014
国/地域	ギリシャ
City	Hersonissos, Crete Island
Period	9/1/14 → 9/4/14

!!!All Science Journal Classification (ASJC) codes

コンピュータサイエンスの応用
コンピュータビジョンおよびパターン認識

文献へのアクセス

10.1109/ICFHR.2014.29

他のファイルとリンク

引用スタイル

Frinken, V., Kakisako, R., & Uchida, S. (2014). A Novel HMM Decoding Algorithm Permitting Long-Term Dependencies and Its Application to Handwritten Word Recognition. In Proceedings - 14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014 (pp. 128-133). Article 6981008 (Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR; Vol. 2014-December). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICFHR.2014.29

A Novel HMM Decoding Algorithm Permitting Long-Term Dependencies and Its Application to Handwritten Word Recognition. / Frinken, Volkmar; Kakisako, Ryosuke; Uchida, Seiichi.
Proceedings - 14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 128-133 6981008 (Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR; Vol. 2014-December).

研究成果: 書籍/レポートタイプへの寄稿 › 会議への寄与

Frinken, V, Kakisako, R & Uchida, S 2014, A Novel HMM Decoding Algorithm Permitting Long-Term Dependencies and Its Application to Handwritten Word Recognition. in Proceedings - 14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014., 6981008, Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR, vol. 2014-December, Institute of Electrical and Electronics Engineers Inc., pp. 128-133, 14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014, Hersonissos, Crete Island, ギリシャ, 9/1/14. https://doi.org/10.1109/ICFHR.2014.29

Frinken V, Kakisako R, Uchida S. A Novel HMM Decoding Algorithm Permitting Long-Term Dependencies and Its Application to Handwritten Word Recognition. In Proceedings - 14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 128-133. 6981008. (Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR). doi: 10.1109/ICFHR.2014.29

Frinken, Volkmar ; Kakisako, Ryosuke ; Uchida, Seiichi. / A Novel HMM Decoding Algorithm Permitting Long-Term Dependencies and Its Application to Handwritten Word Recognition. Proceedings - 14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 128-133 (Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR).

@inproceedings{d619574288ef4109830138b7c03e28f6,

title = "A Novel HMM Decoding Algorithm Permitting Long-Term Dependencies and Its Application to Handwritten Word Recognition",

abstract = "A new decoding for hidden Markov models is presented. As opposed to the commonly used Viterbi algorithm, it is based on the Min-Cut/Max-Flow algorithm instead of dynamic programming. Therefore non-Markovian long-term dependencies can easily be added to influence the decoding path while still finding the optimal decoding in polynomial time. We demonstrate through an experimental evaluation how these constraints can be used to improve an HMM-based handwritten word recognition system that model words via linear character-HMM by restricting the length of each character.",

author = "Volkmar Frinken and Ryosuke Kakisako and Seiichi Uchida",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014 ; Conference date: 01-09-2014 Through 04-09-2014",

year = "2014",

month = dec,

day = "9",

doi = "10.1109/ICFHR.2014.29",

language = "English",

series = "Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "128--133",

booktitle = "Proceedings - 14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014",

address = "United States",

}

TY - GEN

T1 - A Novel HMM Decoding Algorithm Permitting Long-Term Dependencies and Its Application to Handwritten Word Recognition

AU - Frinken, Volkmar

AU - Kakisako, Ryosuke

AU - Uchida, Seiichi

PY - 2014/12/9

Y1 - 2014/12/9

N2 - A new decoding for hidden Markov models is presented. As opposed to the commonly used Viterbi algorithm, it is based on the Min-Cut/Max-Flow algorithm instead of dynamic programming. Therefore non-Markovian long-term dependencies can easily be added to influence the decoding path while still finding the optimal decoding in polynomial time. We demonstrate through an experimental evaluation how these constraints can be used to improve an HMM-based handwritten word recognition system that model words via linear character-HMM by restricting the length of each character.

AB - A new decoding for hidden Markov models is presented. As opposed to the commonly used Viterbi algorithm, it is based on the Min-Cut/Max-Flow algorithm instead of dynamic programming. Therefore non-Markovian long-term dependencies can easily be added to influence the decoding path while still finding the optimal decoding in polynomial time. We demonstrate through an experimental evaluation how these constraints can be used to improve an HMM-based handwritten word recognition system that model words via linear character-HMM by restricting the length of each character.

UR - http://www.scopus.com/inward/record.url?scp=84942236657&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84942236657&partnerID=8YFLogxK

U2 - 10.1109/ICFHR.2014.29

DO - 10.1109/ICFHR.2014.29

M3 - Conference contribution

AN - SCOPUS:84942236657

T3 - Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR

SP - 128

EP - 133

BT - Proceedings - 14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014

Y2 - 1 September 2014 through 4 September 2014

ER -

A Novel HMM Decoding Algorithm Permitting Long-Term Dependencies and Its Application to Handwritten Word Recognition

抄録

出版物シリーズ

その他

!!!All Science Journal Classification (ASJC) codes

文献へのアクセス

他のファイルとリンク

フィンガープリント

引用スタイル