Abstract
In this paper, we propose a new approach for off-line intelligent word recognition. Firstly, we segment a word into its single characters. Then, we tag every pixel of a character as vertical or horizontal and group them into vertical and horizontal strokes. We propose as main features the locations of the joints between a vertical stroke and each of their adjacent horizontal ones. These features can easily be obtained by dynamic zoning. After that, a Deterministic Finite Automaton (DFA) along with a regular grammar, let us generate a representative string of the above mentioned features. For the experiments we constructed sets of synthetic words from real characters written by two different authors to generate a knowledge base for each of the writers with the strings provided by the DFA. To achieve the recognition, we use an Inference Engine that matches representative strings of characters from unknown test words with those characters stored in the Knowledge Base. The experiments provide promising results.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Rahman AFR, Fairhurst MC (1998) Machine-printed character recognition revisited: re-application of recent advances in handwritten character recognition research. Image Vis Comput 16(12–13):819–842
Alabau V, Martínez-Hinarejos C-D, Romero V, Lagarda A-L (2014) An iterative multimodal framework for the transcription of handwritten historical documents. Pattern Recogn Lett 35:195–203
Vicent A, Alberto S, Francisco C (2014) Improving on-line handwritten recognition in interactive machine translation. Pattern Recogn 47(3):1217–1228
AlKhateeb Jawad H, Olivier P, Jinchang R, Jianmin J (2011) Performance of hidden Markov model and dynamic Bayesian network classifiers on handwritten Arabic word recognition. Knowl Based Syst 24(5):680–688
Alonso A, Fernández RA, García I (2005) Recognition of merged characters based on vertical strokes and adjacency regions. In: V Congress of Hispalinux, pp 1–23
Álvaro F, Sánchez J-A, Benedí J-M (2014) Recognition of on-line handwritten mathematical expressions using 2D stochastic context-free grammars and hidden Markov models. Pattern Recogn Lett 35:58–67
Bertolami R, Bertolami R, Uchida S, Uchida S, Zimmermann M, Zimmermann M, Bunke H, Bunke H (2007) Non-uniform slant correction for handwritten text line recognition. In: Ninth International Conference on Document Analysis and Recognition (ICDAR 2007), pp 18–22
Caesar T, Gloger JM, Mandler E (1993) Preprocessing and feature extraction for a handwriting recognition system. In Proceedings of the Second International Conference on Document Analysis and Recognition, pp 408–411
Djeddi C, Siddiqi I, Souici-Meslati L, Ennaji A (2013) Text-independent writer recognition using multi-script handwritten texts. Pattern Recogn Lett 34(10):1196–1202
Dunn CE, Wang PSP (1992) Character segmentation techniques for handwritten text-a survey. In Pattern Recognition, 1992. Vol. II. Conference B: Pattern Recognition Methodology and Systems, Proceedings., 11th IAPR International Conference on, pp 577–580
Dzuba G, Filatov A, Volgunin A (1997) Handwritten zip code recognition. Analysis and Recognition, vol 1, pp 766–770
Adrià G, Ihab K, Jesús A-F, Alfons J (2014) Handwriting word recognition using windowed Bernoulli HMMs. Pattern Recogn Lett 35:149–156
Haji M, Bui TD, Suen CY (2012) Removal of noise patterns in handwritten images using expectation maximization and fuzzy inference systems. Pattern Recogn 45(12):4237–4249
Hanmandlu M, Murali Mohan KR, Chakraborty S, Goyal S, Roy Choudhury D (2003) Unconstrained handwritten character recognition based on fuzzy logic. Pattern Recogn 36(3):603–623
Jain AK, Griess FD, Connell SD (2002) On-line signature veriÿcation. 35:2963–2972
Jiang D, Mekonnen TM, Merkebu TE, Gebrehiwot A (2012) Car Plate Recognition System. In: 2012 Fifth International Conference on Intelligent Networks and Intelligent Systems, pp 9–12
Kessentini Y, Paquet T, Hamadou AMB (2010) Off-line handwritten word recognition using multi-stream hidden markov models. Pattern Recogn Lett 31(1):60–70
Liu C-L, Nakashima K, Sako H, Fujisawa H (2004) Handwritten digit recognition: investigation of normalization and feature extraction techniques. Pattern Recogn 37(2):265–279
Louloudis G, Gatos B, Pratikakis I, Halatsis C (2009) Text line and word segmentation of handwritten documents. Pattern Recogn 42(12):3169–3183
Morita ME, Letelier E (2000) Recognition of handwritten dates on bank checks using an HMM approach. Graphics and Image, pp 113–120
Il-Seok Oh, Suen CY (2002) A class-modular feedforward neural network for handwriting recognition. Pattern Recogn 35(1):229–244
Palacios R, Gupta A (2003) Training neural networks for reading handwritten amounts on checks. In: 2003 IEEE 13th Workshop on Neural Networks for Signal Processing, NNSP’03, pp 607–616
Zhang P, Chen L (2002) A novel feature extraction method and hybrid tree classification for handwritten numeral recognition. 23:45–56
Plamondon R, Srihari SN (2000) Online and off-line handwriting recognition: a comprehensive survey. IEEE Trans Pattern Anal Mach Intell 22(1):63–84
Namane RA, Guessoum A, Soubari EH, Meyrueis P (2014) CSM neural network for degraded printed character optical recognition. J Vis Commun Image Represent 25(5):1171–1186
Schlapbach A, Liwicki M, Bunke H (2008) A writer identification system for on-line whiteboard data. Pattern Recogn 41(7):2381–2397 July
Takahashi H, Itoh N, Amano T, Yamashita A (1990) A spelling correction method and its application to an OCR system. Pattern Recogn 23(3):363–377
Toselli AH, Juan A, Vidal E (2004) Spontaneous handwriting recognition and classification. ICPR 1:433–436
Zimmermann M, Bunke H (2002) Automatic segmentation of the IAM off-line database for handwritten English text. Object recognition supported by user interaction for service robots, 4(c)
Zou Y, Dong F, Lei B, Sun S, Jiang T, Chen P (2014) Maximum similarity thresholding. Digit Signal Proc 1:1–16
Trier ID, Jain AK, Taxt T (1996) Feature extraction methods for character recognition-a survey. Pattern Recogn 29(4):641–662
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Álvarez, D., Fernández, R., Sánchez, L. (2015). Stroke-Based Intelligent Word Recognition Using a Formal Language. In: Herrero, Á., Sedano, J., Baruque, B., Quintián, H., Corchado, E. (eds) 10th International Conference on Soft Computing Models in Industrial and Environmental Applications. Advances in Intelligent Systems and Computing, vol 368. Springer, Cham. https://doi.org/10.1007/978-3-319-19719-7_9
Download citation
DOI: https://doi.org/10.1007/978-3-319-19719-7_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-19718-0
Online ISBN: 978-3-319-19719-7
eBook Packages: EngineeringEngineering (R0)