Abstract.
This paper presents an HMM-MLP hybrid system for segmenting and recognizing complex date images written on Brazilian bank checks. Through the recognition process, the system makes use of an HMM-based approach to segment a date image into subfields. Then the three obligatory date subfields (day, month, and year) are processed. A neural approach has been adopted to decipher strings of digits (day and year) and a Markovian strategy to recognize and verify words (month). The final decision module makes an accept/reject decision. We also introduce the concept of metaclasses of digits to reduce the lexicon size of the day and year and improve the precision of their segmentation and recognition. Experiments show interesting results on date recognition.
Similar content being viewed by others
References
Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, Oxford, UK
Britto Jr A, Sabourin R, Bortolozzi F, Suen CY (2001) A two-stage HMM-based system for recognizing handwritten numeral strings. In: Proceedings of the 6th ICDAR, Seattle, September 2001, pp 396-400
De Oliveira Jr JJ, de Carvalho JM, de A Freitas CO, Sabourin R (2002) Feature sets evaluation for handwritten word recognition. In: Proceedings of the 8th IWFHR, Niagara on the Lake, CA, August 2002, pp 446-451
Favata JT, Srihari SN, Govindaraju V (1998) Off-line handwritten sentence recognition. In: Proceedings of the 6th IWFHR, Taegon, South Korea, August 1998, pp 171-176
Fumera G, Roli F, Giacinto G (2000) Reject option with multiple thresholds. Patt Recog 12:2099-2101
Ghosh J (2002) Multiclassifier systems: back to the future. In: Proceedings of the 3rd international workshop on multiple classifier systems, Cagliari, Italy, June 2002, pp 1-15
Gorski N, Anisimov V, Augustin E, Baret O, Maximov S (2001) Industrial bank check processing: the A2iA checkreader. Int J Doc Anal Recog 3:196-206
Ha TM, Bunke H (1997) Off-line, handwritten numeral recognition by perturbation method. IEEE Trans Patt Anal Mach Intell 19(5):535-539
Heutte L, Moreau J, Plessis B, Plagmaud J, Lecourtier Y (1993) Handwritten numeral recognition based on multiple feature extractors. In: Proceedings of the 2nd ICDAR, Tsukuba, Japan, October 1993, pp 167-170
Huang XD, Ariki Y, Jack MA (1990) Hidden Markov models for speech recognition. Edinburgh University Press, Edinburgh, UK
Jelinek F (1997) Statistical methods for speech recognition. MIT Press, Cambridge, MA
Kaufmann G, Bunke H (2000) Automated reading of cheque amounts. Patt Anal Appl 3:132-141
Kim G, Govindaraju V (1998) Handwritten phrase recognition as applied to street name images. Patt Recog 31(1):41-51
Kumar S, Ghosh J, Crawford MM (2002) Hierarchical fusion of multiple classifiers for hyperspectral data analysis. Patt Anal Appl 5(2):210-220
Lippmann RP (1989) Pattern classification using neural networks. IEEE Commun Mag 27(11):47-64
Marti U, Bunke H (2001) Text line segmentation and word recognition in a system for general writer independent handwriting recognition. In: Proceedings of the 6th ICDAR, Seattle, September 2001, pp 159-163
Marti U, Bunke H (2001) Using a statistical language model to improve the performance of an HMM-based cursive handwriting recognition system. Int J Patt Recog Artif Intell 15(1):65-90
Mohamed MA, Gader P (1996) Handwritten word recognition using segmentation-free hidden Markov modeling and segmentation-based dynamic programming techniques. IEEE Trans Patt Anal Mach Intell 18(5):548-554
Morita M, El Yacoubi A, Sabourin R, Bortolozzi F, Suen CY (2001) Handwritten month word recognition on Brazilian bank cheques. In: Proceedings of the 6th ICDAR, Seattle, September 2001, pp 972-976
Morita M, Sabourin R, Bortolozzi F, Suen CY (2002) Segmentation and recognition of handwritten dates. In: Proceedings of the 8th IWFHR, Niagara on the Lake, CA, August 2002, pp 105-110
Oliveira LS, Sabourin R, Bortolozzi F, Suen CY (2002) Automatic recognition of handwritten numerical strings: a recognition and verification strategy. IEEE Trans Patt Anal Mach Intell 24(11):1438-1454
Park J, Govindaraju V (2002) Use of adaptive segmentation in handwritten phrase recognition. Patt Recog 35:245-252
Park J, Govindaraju V, Srihari SN (1999) Efficient word segmentation driven by unconstrained handwritten phrase recognition. In: Proceedings of the 5th ICDAR, Bangalore, India, September 1999, pp 605-608
Rabiner LR (1989) A tutorial on hidden Markov models and selected applications in speech recognition. IEEE 77(2):257-286
Srihari SN, Govindaraju V, Shekhawat A (1993) Interpretation of handwritten address in us mailstream. In: Proceedings of the 2nd ICDAR, Tsukuba, Japan, October 1993, pp 291-294
Suen CY, Xu Q, Lam L (1999) Automatic recognition of handwritten data on cheques - fact or fiction? Patt Recog Lett 20(13):1287-1295
Xu Q, Kim JH, Lam L, Suen CY (2002) Recognition of handwritten month words on bank cheques. In: Proceedings of the 8th IWFHR, Niagara on the Lake, CA, August 2002, pp 111-116
Xu Q, Lam L, Suen CY (2001) A knowledge-based segmentation system for handwritten dates on bank cheques. In: Proceedings of the 6th ICDAR, Seattle, September 2001, pp 384-388
El Yacoubi M, Gilloux M, Bertille JM (2002) A statistical approach for phrase location and recognition within a text line: an application to street name recognition. IEEE Trans Patt Anal Mach Intell 24(2):172-188
Author information
Authors and Affiliations
Corresponding author
Additional information
Received: 17 December 2002, Accepted: 16 July 2003, Published online: 17 November 2003
Correspondence to: Marisa Morita
Rights and permissions
About this article
Cite this article
Morita, M., Sabourin, R., Bortolozzi, F. et al. Segmentation and recognition of handwritten dates: an HMM-MLP hybrid approach. IJDAR 6, 248–262 (2003). https://doi.org/10.1007/s10032-003-0114-z
Issue Date:
DOI: https://doi.org/10.1007/s10032-003-0114-z