Introdução ao Reconhecimento de Palavras Manuscritas

DOI: http://dx.doi.org/10.12721/2237-5112.v02n01a05

http://www.rtic.com.br

Luciana R. Veloso¹ & Francisco Madeiro²

Resumo: O avanço do conhecimento, a expansão da memória e a comunicação estão entre os benefícios proporcionados pela escrita, que constitui-se em um dos objetos da área de processamento de documentos. Dentre os desenvolvimentos relacionados a esta área, podem ser citados: sistemas de reconhecimento de caracteres manuscritos, de assinaturas, de numerais manuscritos, de palavras manuscritas e sistemas de filtragem frente-verso. Este artigo apresenta uma introdução ao reconhecimento de palavras manuscritas. São abordadas etapas importantes do sistemas de reconhecimento: pré-processamento, segmentação e classificação. O artigo aborda, ainda, técnicas utilizadas para o propósito do reconhecimento, com destaque para os modelos de Markov escondidos, as redes neurais artificiais e os métodos híbridos.

Palavras-chave: Processamento de documentos, reconhecimento de manuscritos, reconhecimento de palavras manuscritas, processamento digital de imagens, reconhecimento de padrões

¹ Universidade Federal de Campina Grande (UFCG), Campina Grande, PB, Brasil. E-mail: veloso@dee.ufcg.edu.br

² Escola Politécnica de Pernambuco (POLI), Universidade de Pernambuco (UPE), Recife, PE, Brasil. E-mail: madeiro@poli.br

Literatura Citada

[1] Plamondon, R. and Srihari, S. N., “On-Line and Off-Line Handwriting Recognition: A Comprehensive Survery,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.22, No.1, pp. 63–84, January 2000. 

[2] Koerich, A. L., Sabourin, R. and Suen, C. Y., “Large Vocabulary Off-line Handwriting Recognition: A survey,” Pattern Analysis and Applications, vol. 6, pp. 97–121, 2003. 

[3] Buse, R., Liu, Z.-Q. and Caelli, T. , “A Structural and Relational Approach to Handwritten Word Recognition,” IEEE Transactions on Systems, Man and Cybernetics - Part B: Cybernetics, Vol. 27, No. 5, pp. 847–861, October 1997. 

[4] El-Yacoubi, A., Gilloux, M., Sabourin, R. and Suen, C. Y., “Unconstrained Handwritten Word Recognition using Hidden Markov Models,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993. 

[5] Bozinovic, R. M., and Shihari, S. N., “Off-Line Cursive Script Word Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.11, No.1, pp. 68–83, January 1989. 

[6] Kim, G. and Govindaraju, V., “A Lexicon Driven Approach to Handwritten Word Recognition for Real-Time Applications ,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19, No. 4, pp. 366–379, April 1997. 

[7] Kim, G. and Govindaraju, V. , “Handwritten Phrase Recognition as Applied to Street Name Images,” Pattern Recognition, Vol. 31, No. 1, pp. 41–51, 1998. 

[8] Ding, Y., Kimura, F., Miyake, Y. and Shridhar, M., “Accuracy Improvement of Slant Estimation for Handwritten Words,” Proceedings of the International Conference on Pattern Recognition - ICPR’00, pp. 527–530, 2000. 

[9] Slavík, P. and Govindaraju, V., “Equivalence of Different Methods for Slant and Skew Corrections in Word Recognition Applications,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.23, No.3, pp. 323–326, March 2001. 

[10] Côté, M., Lecolinet, E., Cheriet, M. and Suen, C. Y. , “Automatic Reading of Cursive Scripts Using a Reading Model and Perceptual Concepts,” International Journal on Document Analysis and Recognition, Vol. 1, pp. 3–17, 1998. 

[11] Senior, A. W. and Robinson, A. J. , “An Off-Line Cursive Handwriting Recognition System,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 20, No. 3, pp. 309–321, March 1998. 

[12] Parker, J. R., Algorithms For Image Processing and Computer Vision. Wiley Computer Publishing, 1997. 

[13] Facon, J., Morfologia Matem´atica: Teoria e Exemplos., Universit´aria, Ed. PUC-PR, 1996. 

[14] Frucci, M. and Marcelli, A. , “Contour Pixel Classification for Character Skeletonization,” Proceedings of the First Brazilian Symposium of Document Image Analysis, pp. 141–152, November 1997. 

[15] Borgefors, G., Ramella, G. and Baja, G. S. , “Using Binary Pyramids to Create Multi-resolution Shape Descriptors,” Proceedings of the First Brazilian Symposium of Document Image Analysis, pp. 129–140, November 1997. 

[16] Gonzalez, R. C. and Woods, R. E. , Digital Image Processing, Addison-Wesley, Ed., 1992. 

[17] Lam, L. and Suen, C. Y. , “An Evaluation of Parallel Thinning Algorithms for Character Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 17, No. 9, pp. 914–919, 1995. 

[18] El Yacoubi, A., “Mod´elisation Markovienne de L’´Ecriture Manuscrite Application `a la Reconnaissance des Adresses Postales,” Thesis, Universite De Rennes 1, 1996. 

[19] El-Yacoubi, A., Gilloux, M., Sabourin, R. and Suen, C. Y., “An HMM-Based Approach for Off-Line Unconstrained Handwritten Word Modeling and Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 21, No. 8, pp. 752–760, August 1999. 

[20] Freitas, C., El-Yacoubi, A., Bortolozzi, F. and Sabourin, A., “Brazilian Bank Check Handwritten Legal Amount Recognition,” Anais do Simpósio Brasileiro de Computação Gráfica e Processamento de imagens- SIBGRAPI’2000, 2000. 

[21] Casey, R.G. and Lecolinet E. , “A Survey of Methods and Strategies in Character Segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 18, No. 7, pp. 690–706, 1996. 

[22] Veloso, L. R., “Sistema de Reconhecimento de Palvras Manuscritas Dependente do Usuário,” Tese de Doutorado, Universidade Federal de Campina Grande, UFCG, Brasil, março 2009. 

[23] Mohamed, M. A. and Gader, P., “Generalized Hidden Markov Models - Part I: Theoretical Frameworks,” IEEE Transactions on Fuzzy Systems, vol. 8, no. 1, pp. 67–81, 2000. 

[24] Kim, J. H., Kim, K. K., Nadal, C. and Suen, C., “A methodology of Combining HMM and MLP Classifiers for Cursive Word Recognition,” Proceedings of the International Conference on Pattern Recognition - ICPR’00, pp. 319–322, 2000. 

[25] Kundu, M. and Bahl, P., “Recognition of handwritten script: A hidden markov model based approach,” Relatório Técnico, 1988. 

[26] Oliveira Jr., J. J., “Reconhecimento de Palavras Manuscritas Usando An´alise Multi-Vistas,” Tese de Doutorado, Universidade Federal de Campina Grande, 2006. 

[27] Grandidier, F., Sabourin, R., El-Yacoubi, A., Gilloux, M. and Suen, C., “Influence of Word Length on Handwriting Recognition,” 1999. [Online]. Available: http://citeseer.ist.psu.edu/grandidier99influence.html 

[28] Nunes, C. M., Britto, Ad. S., Jr.; Kaestner, C. A. A.; Sabourin, R., “An Optimized Hill Climbing Algorithm for Feature Subset Selection: Evaluation on Handwritten Character Recognition,” in Ninth International Workshop on Frontiers in Handwriting Recognition, 2004. 

[29] Oliveira, L. S., Sabourin, R., Bortolozzi, F. and Suen, C. Y. , “A Methodology for Feature Selection Using Multi-Objective Genetic Algorithms for Handwritten Digit String Recognition,” International Journal of Pattern Recognition and Artificial Intelligence, vol. 17, pp. 903–930, 2003. 

[30] Morita, M., Oliveira, L.S. and Sabourin, R., “Geração Automática de Conjuntos de Classificadores Através da Seleção de Caracteríticas não Supervisionada,” IEEE Latin America Transactions, vol. 3, no. 5, pp. 50–56, 2005. 

[31] Oliveira, L. S., Morita, M. and Sabourin, R., “Feature Selection for Ensembles Applied to Handwriting Recognition,” International Journal on Document Analysis and Recognition, vol. 8, no. 4, pp. 262–279, 2006. 

[32] Kim, J. H., Kim, K. K. and Suen, C. Y., “An HMM-MLP Hybrid Model for Cursive Script Recognition,” Pattern Analysis and Applications, vol. 3, pp. 314–324, 2000. 

[33] Li, Z.C., Suen, C.Y., Guo, J., “A Regional Decomposition Method for Recognizing Handprinted Characters,” IEEE Transactions on Systems, Man, and Cybernetics, pp. 998–1010, 1995. 

[34] Xu, L., Krzyzak, A. and Suen, C.,Y., “Methods of Combining Multiple Classifiers and Their Applications to Handwriting Recognition,” IEEE Transactions on Systems, Man, and Cybernetics, Vol.22, No.3, pp. 418–435, May/June 1992. 

[35] Suen, C., Kim, J., Kim, K., Xu, Q. and Lam, L., “Handwriting Recognition - The Last Frontiers,” Proceedings of the International Conference on Pattern Recognition - ICPR’00, pp. 1–10, September 2000. 

[36] Brakensiek, A., Kosmala, A., Willet, D., Wang, W. and Rigoll G., “Performance Evaluation of a New Modeling Technique for Handwriting Recognition Using Identical On-Line and Off- Line Data,” Proceedings of the V International Conference on Document Analysis and Recognition - ICDAR’99, Bangalore, India, 1999. 

[37] Dehghan, M., Faez, K., Ahmadi, M. and Shridhar, M., “Off-Line Unconstrained Farsi Handwritten Word Recognition Using Fuzzy Vector Quantization and Hidden Markov Word Models,” Proceedings of the International Conference on Pattern Recognition - ICPR’00, pp. 351–354, September 2000. 

[38] Knerr, S. and Augustian, E., “A Neural Network-Hidden Markov Model Hybrid for Cursive Word Recognition,” Proceedings of the International Conference on Pattern Recognition - ICPR’98, Vol. 2, pp. 1518–1520, 1998. 

[39] Ko A., Sabourin R., Britto Jr. A. and Oliveira L. S., “Pairwise Fusion Matrix for Combining Classifiers,” Pattern Recognition, vol. 40, no. 8, pp. 2198–2210, 2007. 

[40] Oliveira, L. S. Sabourin, R., Bortolozzi, F. and Suen, C. Y., “Feature Selection for Ensembles: A Hierarchical Multi-Objective Genetic Algorithm Approach,” in In Proc. of 7 th International Conference on Document Analysis and Recognition, Edinburgh-Scotland, 2003. IEEE Computer Society, 2003, pp. 676–680. 

[41] Morita, M., Oliveira, L. S. and Sabourin, R., “Unsupervised Feature Selection for Ensemble of Classifiers,” in In 9th International Workshop on Frontiers in Handwriting Recognition, 2004, pp. 81–86. 

[42] Liu, C.-L. and Marukawa, K., “Normalization Ensemble for Handwritten Character Recognition,” International Workshop on Frontiers in Handwriting Recognition,, vol. 0, pp. 69–74, 2004. 

[43] Srihari, S. N., Xu, A. and Kalera, M., “Learning Strategies and Classification Methods for Off-Line Signature Verification,” International Workshop on Frontiers in Handwriting Recognition, vol. 0, pp. 161–166, 2004. 

[44] Haykin, S., Neural Networks - A Comprehensive Foundation. Upper Saddle River, New Jersey 07458: Prentice-Hall, Inc., 1999. 

[45] Beale, R. and Jackson, T., Neural Computing: An Introduction. Bristol and Philadelphia: Institute of Physics Publishing, 1990. 

[46] Kohonen, T., Self-Organization and Associative Memory (3rd ed). Berlin: Springer-Verlag, 1989. 

[47] Gader, P., Whalen, M., Ganzberger, M. and Hepp, D. , “Handprinted Word Recongition on a NIST Data Set,” Machine Vision and Application, Vol.8, pp. 31–40, 1995. 

[48] Gader, P., Mohamed, M. and Chiang, J.-H. , “Comparison of Crisp and Fuzzy Character Neural Networks in Handwritten Word Recognition,” IEEE Transactions on Fuzzy Systems, Vol. 3, No. 3, pp. 357–363, August 1995. 

[49] Rabiner, L. R. and Schafer, R. W., Digital Processing of Speech Signals. Upper Saddle River, New Jersey: Prentice-Hall, 1978. 

[50] Mohamed, M. A. and Gader, P, “Handwritten Word Recognition Using Segmentation-Free Hidden Markov Modeling and Segmentation-Based Dynamic Programming Techniques,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 18, No. 5, pp. 548–554, May 1996. 

[51] Mohamed, M. A. and Gader, P., “Generalized Hidden Markov Models - Part II: Application to Handwritten Word Recognition,” IEEE Transactions on Fuzzy Systems, vol. 8, no. 1, pp. 82–94, 2000. 

[52] Gillies, A.M., “Cursive Word Recognition Using Hidden Markov Models,” Proceedings of the Advanced Technology Conference - United States Postal Service, Vol. 1, 1992. 

[53] Chen, M.-Y., Kundu, A., Zhou, J. and Srihari, S. N., “Off-Line Handwritten Word Recognition Using Hidden Markov Models,” Proceedings of the Advanced Technology Conference - United States Postal Service, Vol. 1, 1992. 

[54] Chen, M.-Y., Kundu, A. and Zhou, J., “Off-Line Handwritten Word Recognition Using Hidden Markov Model Type Stochastic Network ,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.16, No. 5, pp. 481–496, May 1994. 

[55] Chen, M.-Y., Kundu, A. and Srihari, N. , “Variable Duration Hidden Markov Model and Morphological Segmentation for Handwritten Word Recognition,” IEEE Transactions on Image Processing, Vol. 4, No. 12, pp. 1675 – 1687, December 1995. 

[56] Gilloux, M., Leroux, M. and Bertille, J.-M. , “Strategies for Hanwritten Words Recognition Using Hidden Markov Models,” Proceedings of the International Conference on Document Analysis and Recognition - ICDAR’93, pp. 299–304, 1993. 

[57] Bunke, H., Roth, M. and Schukatt-Talamazzini, E.G., “Off-line Cursive Handwriting Recognition using Hidden Markov Models,” Relatório Técnico, IAM-94-008, Institut fúr Informatik und angewandle Mathematic, Universität Bern, 1994. 

[58] Wang, W., Brakensiek, A., Kosmala and Rigoll G. , “HMM Based High Accuracy Off-Line Cursive Handwriting Recognition by a Baseline Detection Error Tolerant Feature Extraction Approach,” Proceedings of the IWFHR, Amsterdam, The Netherlands, 2000. 

[59] Brakensiek, A., Rottland, A., Kosmala, A., and Rigoll G. , “Off-Line Handwriting Recognition Using Various Hybrid Modeling Techniques and Character N-Grams,” Proceedings of the IWFRH, Amsterdam, The Netherlands, 2000. 

[60] Guillevic, D. and Suen, C. Y., “HMM Word Recognition Engine,” Proceedings of the IV International Conference on Document Analysis and Recognition - ICDAR’97, Ulm , Germany, pp. 544–547, 1997. 

[61] Kim, G., and Kim, S. , “Feature Selection Using Genetic Algorithms for Handwritten Character Recognition,” Proceedings of the International Workshop on Frontiers in Handwriting Recognition, Amsterdam, The Netherlands, 2000. 

[62] Arica, N. and Yarman-Vural, F. T., “Optical Character Recognition for Cursive Handwriting,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 6, pp. 801–813, 2002. 

[63] Koerich, A. and Sabourin, R. and Suen, C. Y., “Fast Two-Level HMM Decoding Algorithm for Large Vocabulary Handwriting Recognition,” in Proc. Ninth Workshop Frontiers in Handwriting Recognition, 2004, pp. 232–237. 

[64] Kessentini, Y., Paquet, T. and Benhamadou, A., “A Multi-stream Approach to Off-Line Handwritten Word Recognition,” in ICDAR ’07: Proceedings of the Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 1. Washington, DC, USA: IEEE Computer Society, 2007, pp. 317–321. 

[65] Koch, G., Paquet, T. and Heutte, L., “Combination of Contextual Information for Handwritten Word Recognition,” in Proceedings of the Ninth International Workshop on Frontiers in Handwriting Recognition. Washington, DC, USA: IEEE Computer Society, 2004, pp. 468–473. 

[66] Shetty, S., Srinivasan, H. and Srihari, S., “Handwritten Word Recognition Using Conditional Random Fields,” in Proceedings of the Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 2. Washington, DC, USA: IEEE Computer Society, 2007, pp. 1098–1102.