A novel word spotting method based on recurrent neural networks

Keyword spotting refers to the process of retrieving all instances of a given keyword from a document. In the present paper, a novel keyword spotting method for handwritten documents is described. It is derived from a neural network-based system for unconstrained handwriting recognition. As such it...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 34(2012), 2 vom: 07. Feb., Seite 211-24
1. Verfasser: Frinken, Volkmar (VerfasserIn)
Weitere Verfasser: Fischer, Andreas, Manmatha, R, Bunke, Horst
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2012
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article Research Support, Non-U.S. Gov't
LEADER 01000naa a22002652 4500
001 NLM208932054
003 DE-627
005 20231224004848.0
007 cr uuu---uuuuu
008 231224s2012 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2011.113  |2 doi 
028 5 2 |a pubmed24n0696.xml 
035 |a (DE-627)NLM208932054 
035 |a (NLM)21646681 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Frinken, Volkmar  |e verfasserin  |4 aut 
245 1 2 |a A novel word spotting method based on recurrent neural networks 
264 1 |c 2012 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 21.05.2012 
500 |a Date Revised 01.03.2012 
500 |a published: Print 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Keyword spotting refers to the process of retrieving all instances of a given keyword from a document. In the present paper, a novel keyword spotting method for handwritten documents is described. It is derived from a neural network-based system for unconstrained handwriting recognition. As such it performs template-free spotting, i.e., it is not necessary for a keyword to appear in the training set. The keyword spotting is done using a modification of the CTC Token Passing algorithm in conjunction with a recurrent neural network. We demonstrate that the proposed systems outperform not only a classical dynamic time warping-based approach but also a modern keyword spotting system, based on hidden Markov models. Furthermore, we analyze the performance of the underlying neural networks when using them in a recognition task followed by keyword spotting on the produced transcription. We point out the advantages of keyword spotting when compared to classic text line recognition 
650 4 |a Journal Article 
650 4 |a Research Support, Non-U.S. Gov't 
700 1 |a Fischer, Andreas  |e verfasserin  |4 aut 
700 1 |a Manmatha, R  |e verfasserin  |4 aut 
700 1 |a Bunke, Horst  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 34(2012), 2 vom: 07. Feb., Seite 211-24  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:34  |g year:2012  |g number:2  |g day:07  |g month:02  |g pages:211-24 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2011.113  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 34  |j 2012  |e 2  |b 07  |c 02  |h 211-24