nips nips2005 nips2005-171 nips2005-171-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Jaety Edwards, David Forsyth
Abstract: We introduce a method to automatically improve character models for a handwritten script without the use of transcriptions and using a minimum of document specific training data. We show that we can use searches for the words in a dictionary to identify portions of the document whose transcriptions are unambiguous. Using templates extracted from those regions, we retrain our character prediction model to drastically improve our search retrieval performance for words in the document.
[1] Early Manuscripts at Oxford University. Bodleian library ms. auct. f. 2.13. http://image.ox.ac.uk/.
[2] J. Edwards, Y.W. Teh, D. Forsyth, R. Bock, M. Maire, and G. Vesom. Making latin manuscripts searchable using ghmm’s. In NIPS 17, pages 385–392. 2005.
[3] G. Kopec and M. Lomelin. Document-specific character template estimation. In Proceedings, Document Image Recognition III, SPIE, 1996.
[4] V. Lavrenko, T. Rath, and R. Manmatha. Holistic word recognition for handwritten historical documents. In dial, pages 278–287, 2004.
[5] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278–2324, 1998.
[6] M. Mohri, F. Pereira, and M. Riley. Weighted finite state transducers in speech recognition. ISCA ITRW Automatic Speech Recognition, pages 97–106, 2000.