摘要: The transcription of written text images is one the most challenging tasks in document analysis since it has to cope with variability and ambiguity encountered handwritten data. Only a very restricted setting, as postal addresses or bank checks, works well enough for commercial applications. In case unconstrained modern text, recent advances have pushed field towards becoming interesting practical For historic data, however, recognition accuracies are still far too low automatic systems. Instead, efforts aim at interactive solutions which computer merely assists an expert creating transcription. this chapter, overview given steps along processing chain from line image final output explained, starting normalization feature representation. Two approaches, based on hidden Markov models neural networks, introduced more detail. Finally, databases software toolkits presented, hints further material provided.
springer.com参考文章(63)
Joshua T. Goodman, A Bit of Progress in Language Modeling Extended Version Microsoft Research. pp. 72- ,(2001)
Steve Young, Gunnar Evermann, Mark Gales, Thomas Hain, Dan Kershaw, Xunying Liu, Gareth Moore, Julian Odell, Dave Ollason, Dan Povey, Valtcho Valtchev, Phil Woodland, The HTK book Cambridge University Engineering Department and Entrophic Cambridge Research Laboratory. ,(1995)
Geoffrey N. Leech, Johansson. Stig, Helen Goodluck, Manual of information to accompany the Lancaster-Oslo : Bergen Corpus of British English, for use with digital computers Department of English, University of Oslo. ,(1978)
Seong-Whan Lee, Advances in Handwriting Recognition ,(1999)
Francisco Casacuberta, Enrique Vidal, Alejandro Hctor Toselli, Multimodal Interactive Pattern Recognition and Applications ,(2011)
Hiroaki Sakoe, Eiji Taira, Seiichi Uchida, Nonuniform Slant Correction for Handwritten Word Recognition IEICE Transactions on Information and Systems. ,vol. 87, pp. 1247- 1253 ,(2004)
David G. Stork, Richard O. Duda, Peter E. Hart, Pattern Classification (2nd ed.) ,(1999)
Thomas G. Dietterich, Machine Learning for Sequential Data: A Review Lecture Notes in Computer Science. pp. 15- 30 ,(2002) , 10.1007/3-540-70659-3_2
Ronan Collobert, Johnny Mariéthoz, Samy Bengio, Torch: a modular machine learning software library IDIAP. ,(2002)
Alessandro Vinciarelli, Offline Cursive Handwriting: From Word To Text Recognition IDIAP. ,(2003)