Language technology for handwritten text recognition

This paper shows how the nowadays prevalent technology used in HTR borrows concepts and methods from the field of ASR; i.e. those based on Hidden Markov Models (HMMs). Additionally, it will be described a HTR approach based on employing Bernoulli distributions rather than Gaussian-Mixture distributions for the HMM-state emission probability of observations. Finally, handwritten text recognition evaluation results are reported for several corpora involving different characteristics and languages.Work supported by the EC (FEDER), the Spanish MEC under the MIPRCV “Consolider Ingenio 2010” research programme (CSD2007- 00018) and the Spanisg Government (MICINN and “Plan E”) under the MITTRAL (TIN2009-14633-C03-01) research project.Toselli, AH.; Serrano Martínez-Santos, N.; Giménez Pastor, A.; Khoury, I.; Juan Císcar, A.; Vidal Ruiz, E. (2012). Language technology for handwritten text recognition. En Advances in Speech and Language Technologies for Iberian Languages. Springer Verlag (Germany). 328:178-186. https://doi.org/10.1007/978-3-642-35292-8_19178186328Likforman-Sulem, L., Zahour, A., Taconet, B.: Text line segmentation of historical documents: a survey. International Journal on Document Analysis and Recognition 9, 123–138 (2007)Wong, K.Y., Wahl, F.M.: Document analysis system. IBM Journal of Research and Development 26, 647–656 (1982)Jelinek, F.: Statistical methods for speech recognition. MIT Press (1998)Katz, S.M.: Estimation of probabilities from sparse data for the language model component of a speech recognizer. In: Proceedings of the IEEE Transactions on Acoustics, Speech and Signal Processing (ICASSP 1987), vol. ASSP-35, pp. 400–401(March 1987)Kneser, R., Ney, H.: Improved backing-off for n-gram language modeling. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 1, pp. 181–184 (1995)Bazzi, I., Schwartz, R., Makhoul, J.: An omnifont open-vocabulary OCR system for English and Arabic. IEEE Transactions on Pattern Analysis and Machine Intelligence 21(6), 495–504 (1999)Toselli, A.H., Juan, A., Keysers, D., González, J., Salvador, I., Ney, H., Vidal, E., Casacuberta, F.: Integrated handwriting recognition and interpretation using finite-state models. International Journal of Pattern Recognition and Artificial Intelligence 18(4), 519–539 (2004)Rabiner, L., Juang, B.H.: Fundamentals of speech recognition. Prentice-Hall, Englewood Cliffs (1993)Giménez, A., Juan, A.: Embedded bernoulli mixture hmms for handwritten word recognition. In: Proceedings of the 10th International Conference on Document Analysis and Recognition, Barcelona, Spain, pp. 896–900. IEEE Computer Society (July 2009)Toselli, A., Juan, A., Vidal, E.: Spontaneous handwriting recognition and classification. In: Proceedings of the International Conference on Pattern Recognition (ICPR 2004), Cambridge, United Kingdom, vol. 1, pp. 433–436 (August 2004)Marti, U.V., Bunke, H.: The IAM-database: an English sentence database for off-line handwriting recognition. International Journal on Document Analysis and Recognition (IJDAR) 5(1), 39–46 (2002)Romero, V., Toselli, A.H., Rodríguez, L., Vidal, E.: Computer Assisted Transcription for Ancient Text Images. In: Kamel, M.S., Campilho, A. (eds.) ICIAR 2007. LNCS, vol. 4633, pp. 1182–1193. Springer, Heidelberg (2007)Pérez, D., Tarazón, L., Serrano, N., Castro, F.M., Ramos-Terrades, O., Juan, A.: The germana database. In: Proceedings of the 10th International Conference on Document Analysis and Recognition, Barcelona, Spain, pp. 301–305. IEEE Computer Society (July 2009)Serrano, N., Juan, A.: The rodrigo database. In: Proceedings of the The Seventh International Conference on Language Resources and Evaluation (LREC 2010), Malta, May 19-21 (2010)Pechwitz, M., Maddouri, S.S., Magn̈er, V., Ellouze, N., Amiri, H.: IFN/ENIT-database of handwritten Arabic words. In: Proc. of the Colloque International Francophone sur l’Ecrit et le Document (CIFED), Hammmamet, Tunisia (October 2002