Seite - 148 - in Document Image Processing
Bild der Seite - 148 -
Text der Seite - 148 -
J. Imaging 2018,4, 15
24. Toselli,A.H.; Juan,A.;GonzĂĄlez, J.; Salvador, I.;Vidal,E.;Casacuberta,F.;Keysers,D.;Ney,H. Integrated
HandwritingRecognitionandInterpretationusingFinite-StateModels. Int. J.PatternRecognit. Artif. Intell.
2004,18, 519â539.
25. TesthyphensâTestinghyphenationpatterns.2018.Availableonline: https://www.ctan.org/tex-archive/
macros/latex/contrib/testhyphens (accessedon5January2018)
26. Kneser, R.; Ney,H. Improvedbacking-off forM-gram languagemodeling. In Proceedings of the 1995
International Conference onAcoustics, Speech, and Signal Processing (ICASSPâ95), Detroit, MI, USA,
9â12May1995;Volume1,pp. 181â184.
27. Stolcke,A. SRILMâAnextensible languagemodelingtoolkit. InProceedingsof the3rdInterspeech,Denver,
CO,USA,16â20September2002;pp. 901â904.
28. Young, S.; Evermann, G.; Gales, M.; Hain, T.; Kershaw, D.; Liu, X.; Moore, G.; Odell, J.; Ollason, D.;
Povey, D.; et al. The HTK Book (for HTK Version 3.4); CambridgeUniversity EngineeringDepartment:
Cambridge,UK,2006.
29. LujĂĄn-Mares,M.; Tamarit,V.;Alabau,V.;MartĂnez-Hinarejos,C.D.; Pastor,M.; Sanchis,A.; Toselli,A.H.
iATROS:ASpeech andHandwritingRecognition System. V Jornadas enTecnologĂas delHabla, 2008;
pp.75â78.Availableonline: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.329.6708&rep=
rep1&type=pdf (accessedon5January2018)
30. Hermansky,H.;Ellis,D.P.W.;Sharma,S. Tandemconnectionist featureextractionforconventionalHMM
systems. In Proceedings of the 2000 IEEE International Conference on Acoustics, Speech, and Signal
Processing(ICASSPâ00), Istanbul,Turkey,5â9 June2000;Volume3,pp. 1635â1638.
31. Graves, A. RNNLIB: A Recurrent Neural Network Library for Sequence Learning Problems. 2016.
Availableonline: http://sourceforge.net/projects/rnnl/(accessedon5January2018)
32. Chammas, E. StructuringHidden Information inMarkovModelingwithApplication toHandwriting
Recognition. Ph.D.Thesis,TelecomParisTech,Paris,France,2017.
33. Simonyan,K.;Zisserman,A.Verydeepconvolutionalnetworksfor large-scale imagerecognition. arXiv2014,
arXiv:1409.1556.
34. Gu, J.;Wang,Z.;Kuen, J.;Ma,L.;Shahroudy,A.;Shuai,B.;Liu,T.;Wang,X.;Wang,G. Recentadvances in
convolutionalneuralnetworks. arXiv 2015, arXiv:1512.07108.
35. Graves, A.; FernĂĄndez, S.; Gomez, F.; Schmidhuber, J. Connectionist temporal classiïŹcation: labeling
unsegmented sequence datawith recurrent neural networks. In Proceedings of the 23rd international
conferenceonMachine learningACM,Pittsburgh,PA,USA,25â29 June2006;pp. 369â376.
36. Zeyer,A.;SchlĂŒter,R.;Ney,H. TowardsOnline-RecognitionwithDeepBidirectionalLSTMAcousticModels.
InProceedingsof the2016INTERSPEECH,SanFrancisco,CA,USA,8â12September2016;pp. 3424â3428.
37. Glorot, X.; Bengio, Y. Understanding the difïŹculty of training deep feedforward neural networks.
InProceedingsof theThirteenthInternationalConferenceonArtiïŹcial IntelligenceandStatistics,Sardinia,
Italy,13â15May2010;pp. 249â256.
38. Kingma,D.;Ba, J. Adam:Amethodforstochasticoptimization. arXiv 2014, arXiv:1412.6980.
39. Tieleman, T.; Hinton, G. Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent
magnitude. COURSERANeuralNetw.Mach. Learn. 2012,4, 26â31.
40. Qian,N.Onthemomentumtermingradientdescent learningalgorithms. NeuralNetw. 1999,12, 145â151.
41. Zeiler,M.D.ADADELTA:anadaptive learningratemethod. arXiv 2012, arXiv:1212.5701.
42. Ioffe,S.;Szegedy,C. Batchnormalization:Acceleratingdeepnetworktrainingbyreducinginternalcovariate
shift. InProceedingsof the InternationalConferenceonMachineLearning,Lille, France, 6â11 July2015;
pp.448â456.
43. Miao,Y.;Gowayyed,M.;Metze,F. EESEN:End-to-endspeechrecognitionusingdeepRNNmodelsand
WFST-baseddecoding. InProceedingsof the2015IEEEWorkshoponAutomaticSpeechRecognitionand
Understanding(ASRU),Scottsdale,AZ,USA,13â17December2015;pp. 167â174.
44. Levenshtein,V.I. Binarycodescapableof correctingdeletions, insertions, andreversals. Sov. Phys. Dokl.
1966,10, 707â710.
45. Knezevic, A. Overlapping ConïŹdence Intervals and Statistical SigniïŹcance; StatNews; Cornell University
StatisticalConsultingUnit: Ithaca,NY,USA,2008;Volume73.
148
zurĂŒck zum
Buch Document Image Processing"
Document Image Processing
- Titel
- Document Image Processing
- Autoren
- Ergina Kavallieratou
- Laurence Likforman-Sulem
- Herausgeber
- MDPI
- Ort
- Basel
- Datum
- 2018
- Sprache
- deutsch
- Lizenz
- CC BY-NC-ND 4.0
- ISBN
- 978-3-03897-106-1
- Abmessungen
- 17.0 x 24.4 cm
- Seiten
- 216
- Schlagwörter
- document image processing, preprocessing, binarizationl, text-line segmentation, handwriting recognition, indic/arabic/asian script, OCR, Video OCR, word spotting, retrieval, document datasets, performance evaluation, document annotation tools
- Kategorie
- Informatik