Abstract
As a first step of document understanding a digital image of the document to be analyzed or the trajectory of the pen used for writing needs to be captured. From this raw data the relevant document elements (e.g., text lines) need to be segmented. These are then subject to a number of pre-processing steps that aim at reducing the variability in the appearance of the writing by applying a sequence of normalization operations. In order to be processed by a handwriting recognition system based on Markov models, text-line images and raw pen trajectories are then converted into a sequential representation—which is quite straight-forward for online data but requires some “trick” in the offline case. Based on the serialized data representation features are computed that characterize the local appearance of the script. These are fed into a Markov-model based decoder that produces a hypothesis for the segmentation and classification of the analyzed portion of handwritten text—usually as a sequence of word or character hypotheses.
Keywords
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Especially when processing machine printed documents where it is usually clear that the document image only shows the document to be analyzed, this initial segmentation of relevant document structures is referred to as layout analysis (cf. e.g., [1]).
- 2.
As any document analysis system needs to extract relevant textual items, e.g., words or lines, from the document image or the raw pen trajectory prior to recognition, several preprocessing steps are necessary. These perform tasks which can also be termed “segmentation”. Though there are first approaches to perform, e.g., line separations using HMMs [3], in this respect traditional and MM-based systems are still quite similar. Therefore, in this book we focus on the segmentation at the level of character or word sequences where MM-based approaches can show their strengths.
- 3.
The very basic splitting of the input data at this early stage is fundamentally different from the much more complex segmentation of handwriting data into meaningful parts as, e.g., characters or words. See also Sect. 4.1 for a discussion.
References
Mao S, Rosenfeld A, Kanungo T (2003) Document structure analysis algorithms: a literature survey. In: Proceedings of SPIE electronic imaging, pp 197–207
Gader PD, Keller J M, Krishnapuram R, Chiang JH, Mohamed MA (1997) Neuronal and fuzzy methods in handwriting recognition. IEEE Comput 2:79–86
Lu Z, Schwartz R, Raphael C (2000) Script-independent, HMM-based text line finding for OCR. In: Proceedings of international conference on pattern recognition, Barcelona, Spain, pp 551–554
Plötz T, Thurau C, Fink GA (2008) Camera-based whiteboard reading: new approaches to a challenging task. In: Proceedings of international conference on frontiers in handwriting recognition, Montreal, Canada, pp 385–390
Duda RO, Hart PE, Stork DG (2000) Pattern classification, 2nd edn. Wiley Interscience, New York
Li Y, Zheng Y, Doermann D, Jaeger S (2008) Script-independent text line segmentation in freestyle handwritten documents. IEEE Trans Pattern Anal Mach Intell 30(8):1313–1329
Likforman-Sulem L, Zahour A, Taconet B (2007) Text line segmentation of historical documents: a survey. Int J Doc Anal Recognit 9(2):123–138
Fujisawa H (2007) Robustness design of industrial strength recognition systems. In: Chaudhuri B (ed) Digital document processing: major diretions and recent advances. Springer, London, pp 185–212
Jaeger S, Manke S, Reichert J, Waibel A (2001) Online handwriting recognition: the NPen++ recognizer. Int J Doc Anal Recognit 3:169–180
Trier OD, Taxt T (1995) Evaluation of binarization methods for document images. IEEE Trans Pattern Anal Mach Intell 17(3):312–315
Guerfali W, Plamondon R (1993) Normalizing and restoring on-line handwriting. Pattern Recognit 26(3):419–431
Tappert C, Suen C, Wakahara T (1990) The state of the art in on-line handwriting recognition. IEEE Trans Pattern Anal Mach Intell 12(8):787–808
Bozinovic RM, Srihari SN (1989) Off-line cursive script word recognition. IEEE Trans Pattern Anal Mach Intell 11(1):69–83
Schenkel M, Guyon I, Henderson D (1994) On-line cursive script recognition using time delay neural networks and hidden Markov models. In: Proceedings of international conference on acoustics, speech, and signal processing, Adelaide, Australia, vol 2, pp 637–640
Vinciarelli A, Luettin J (2001) A new normalization technique for cursive handwritten words. Pattern Recognit Lett 22(9):1043–1050
Bertolami R, Uchida S, Zimmermann M, Bunke H (2007) Non-uniform slant correction for handwritten text line recognition. In: Proceedings of international conference on document analysis and recognition, Curitiba, Brazil, vol 1, pp 18–22
Ding Y, Kimura F, Miyake Y, Shridhar M (2000) Accuracy improvement of slant estimation for handwritten words. In: Proceedings of international conference on pattern recognition, Barcelona, Spain, vol 4, pp 527–530
Cai J, Liu ZQ (2000) Off-line unconstrained handwritten word recognition. Int J Pattern Recognit Artif Intell 14(3):259–280
Marti UV, Bunke H (2000) Handwritten sentence recognition. In: Proceedings of international conference on pattern recognition, Barcelona, Spain, vol 3, pp 467–470
Madhvanath S, Kim G, Govindaraju V (1999) Chaincode contour processing for handwritten word recognition. IEEE Trans Pattern Anal Mach Intell 21(9):928–932
Dolfing JGA, Haeb-Umbach R (1997) Signal representations for Hidden Markov Model based on-line handwriting recognition. In: Proceedings of international conference on acoustics, speech, and signal processing, Munich, Germany, vol 4, pp 3385–3388
Caesar T, Gloger JM, Mandler E (1993) Preprocessing and feature extraction for a handwriting recognition system. In: Proceedings of international conference on document analysis and recognition, Tsukuba Science City, Japan, pp 408–411
Schwartz R, LaPre C, Makhoul J, Raphael C, Zhao Y (1996) Language-independent OCR using a continuous speech recognition system. In: Proceedings of international conference on pattern recognition, Vienna, Austria, vol 3, pp 99–103
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2011 Thomas Plötz
About this chapter
Cite this chapter
Plötz, T., Fink, G.A. (2011). General Architecture. In: Markov Models for Handwriting Recognition. SpringerBriefs in Computer Science. Springer, London. https://doi.org/10.1007/978-1-4471-2188-6_2
Download citation
DOI: https://doi.org/10.1007/978-1-4471-2188-6_2
Published:
Publisher Name: Springer, London
Print ISBN: 978-1-4471-2187-9
Online ISBN: 978-1-4471-2188-6
eBook Packages: Computer ScienceComputer Science (R0)