https://oldena.lpnu.ua/handle/ntb/52494| Title: | Improvement of Character Segmentation using Recurrent Neural Networks and Dynamic Programming |
| Authors: | Volkova, Valentyna Deriuga, Ivan Osadchyi, Vadym Radyvonenko, Olga |
| Affiliation: | Samsung R&D Institute Ukraine |
| Bibliographic description (Ukraine): | Improvement of Character Segmentation using Recurrent Neural Networks and Dynamic Programming / Valentyna Volkova, Ivan Deriuga, Vadym Osadchyi, Olga Radyvonenko // Data stream mining and processing : proceedings of the IEEE second international conference, 21-25 August 2018, Lviv. — Львів : Lviv Politechnic Publishing House, 2018. — P. 218–222. — (Dynamic Data Mining & Data Stream Mining). |
| Bibliographic description (International): | Improvement of Character Segmentation using Recurrent Neural Networks and Dynamic Programming / Valentyna Volkova, Ivan Deriuga, Vadym Osadchyi, Olga Radyvonenko // Data stream mining and processing : proceedings of the IEEE second international conference, 21-25 August 2018, Lviv. — Lviv Politechnic Publishing House, 2018. — P. 218–222. — (Dynamic Data Mining & Data Stream Mining). |
| Is part of: | Data stream mining and processing : proceedings of the IEEE second international conference, 2018 |
| Conference/Event: | IEEE second international conference "Data stream mining and processing" |
| Issue Date: | 28-Feb-2018 |
| Publisher: | Lviv Politechnic Publishing House |
| Place of the edition/event: | Львів |
| Temporal Coverage: | 21-25 August 2018, Lviv |
| Keywords: | online handwriting recognition character segmentation recurrent neural networks dynamic programming |
| Number of pages: | 5 |
| Page range: | 218-222 |
| Start page: | 218 |
| End page: | 222 |
| Abstract: | A common characteristic of all the existing online handwritten text recognition algorithms is that the character segmentation process is closely related to the recognition process. There are different approaches to segment data but all of them don’t give absolutely correctly segmentation results due to specifics of handwriting data input. In this paper, we present a new approach for character segmentation improvement in online handwriting recognition which is based on using recurrent neural networks and dynamic programming. Due to online handwritten text is a sequence of points we propose to use Bidirectional Long Short-Term Memory (BLSTM) for classification of decoder outputs and dynamic programming for interpretation of classification results. Experimental evaluation shows the effectiveness of a proposed approach in increasing of segmentation quality. |
| URI: | https://ena.lpnu.ua/handle/ntb/52494 |
| ISBN: | © Національний університет „Львівська політехніка“, 2018 © Національний університет „Львівська політехніка“, 2018 |
| Copyright owner: | © Національний університет “Львівська політехніка”, 2018 |
| URL for reference material: | http://sourceforge.net/projects/rnnl/ |
| References (Ukraine): | [1] R. Plamondon and S. N. Srihari, ”Online and off-line handwriting recognition: a comprehensive survey,” in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 1, pp. 63-84, 2000. [2] C. C. Tappert, C. Y. Suen, T. Wakahara, ”The state of the art in online handwriting recognition,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 12, no. 8, pp. 787-808, 1990. [3] P. Y. Simard, D. Steinkraus and M. Agrawala, ”Ink normalization and beautification,” Eighth International Conference on Document Analysis and Recognition (ICDAR’05), vol. 2, pp. 1182-1187, 2005. [4] R.G. Casey and E. Lecolinet, ”A Survey of Method and Strategies in Character Segmentation,” IEEE Trans. on PAMI, vol. 18 (7), pp. 690-706, 1996. [5] C. T. Nguyen and M. Nakagawa, ”An improved segmentation of online English handwritten text using recurrent neural networks,” 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), Kuala Lumpur, pp. 176-180, 2015. [6] S. P. Naeini, M. Khademi and A. Nikookar, ”A novel approach to segmentation of Persian cursive script using decision tree,” International Journal of Computer Theory and Engineering, vol. 4 (3), p. 465, 2012. [7] I. Mayire, H. Askar and T. Dilmurat, ”A Dynamic Programming Method for Segmentation of Online Cursive Uyghur Handwritten Words into Basic Recognizable Units,” Journal of Software, vol. 10(8), pp. 2535-2540, 2013. [8] E. Kavallieratou, E. Stamatatos, N. Fakotakis and G. Kokkinakis, ”Handwritten character segmentation using transformation-based learning,” Proceedings 15th International Conference on Pattern Recognition. ICPR2000, vol.2, pp. 634-637, 2000. [9] R. Ghosh, ”Stroke segmentation of online handwritten word using the busy zone concept,” 2013 International Conference on Soft Computing and Pattern Recognition (SoCPaR), pp. 54-59, 2013. [10] F. Naohiro, J. Tokuno and H. Ikeda, ”Online character segmentation method for unconstrained handwriting strings using off-stroke features,” Tenth International Workshop on Frontiers in Handwriting Recognition, IWFHR-10, pp. 361-366, 2006. [11] N. Bhattacharya and U. Pal, ”Stroke segmentation and recognition from Bangla online handwritten text,” 2012 International Conference on Frontiers in Handwriting Recognition, pp. 740-745, 2012. [12] I. Mayire, H. Askar, T. Dilmurat, ”A dynamic programming method for segmentation of online cursive Uyghur handwritten words into basic recognizable units,” Journal of Software, vol. 8 (10), pp. 2535-2540, 2013. [13] A. Graves and J. Schmidhuber, ”Framewise phoneme classification with bidirectional LSTM and other neural network architectures,” Neural Networks, v.18 n.5-6, pp. 602-610, 2005. [14] A. Graves, M. Liwicki, S. Fernndez, R. Bertolami, H. Bunke and J. Schmidhuber, ”A novel connectionist system for unconstrained handwriting recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31 (5), pp. 855-868, 2009. [15] A. Graves, ”RNNLIB: A recurrent neural network library for sequence learning problems,” http://sourceforge.net/projects/rnnl/, 2013. [16] E. Indermhle, M. Liwicki and H. Bunke, ”IAMonDo-database: an online handwritten document database with non-uniform contents,” In Proc. Of Int. Workshop on Document Analysis Systems, pp. 97-104, 2010. [17] S. J. Young, N. H. Russell, and J. H. S. Thornton, ”Token passing: A simple conceptual model for connected speech recognition systems,” Tech. Rep. CUED/F-INFENG/TR38, Cambridge University Engineering Department, 1989. [18] F. Chunsheng, ”From Dynamic Time Warping (DTW) to Hidden Markov Model (HMM) Final project report for ECE742 Stochastic Decision,” 2009. [19] V. Khomenko, O. Shyshkov, O. Radyvonenko and K. Bokhan, ”Accelerating recurrent neural network training using sequence bucketing and multi-GPU data parallelization,” Proceedings of the 2016 IEEE First International Conference on Data Stream Mining & Processing, pp. 100-103, 2016. |
| References (International): | [1] R. Plamondon and S. N. Srihari, "Online and off-line handwriting recognition: a comprehensive survey," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 1, pp. 63-84, 2000. [2] C. C. Tappert, C. Y. Suen, T. Wakahara, "The state of the art in online handwriting recognition," IEEE Trans. Pattern Anal. Mach. Intell., vol. 12, no. 8, pp. 787-808, 1990. [3] P. Y. Simard, D. Steinkraus and M. Agrawala, "Ink normalization and beautification," Eighth International Conference on Document Analysis and Recognition (ICDAR’05), vol. 2, pp. 1182-1187, 2005. [4] R.G. Casey and E. Lecolinet, "A Survey of Method and Strategies in Character Segmentation," IEEE Trans. on PAMI, vol. 18 (7), pp. 690-706, 1996. [5] C. T. Nguyen and M. Nakagawa, "An improved segmentation of online English handwritten text using recurrent neural networks," 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), Kuala Lumpur, pp. 176-180, 2015. [6] S. P. Naeini, M. Khademi and A. Nikookar, "A novel approach to segmentation of Persian cursive script using decision tree," International Journal of Computer Theory and Engineering, vol. 4 (3), p. 465, 2012. [7] I. Mayire, H. Askar and T. Dilmurat, "A Dynamic Programming Method for Segmentation of Online Cursive Uyghur Handwritten Words into Basic Recognizable Units," Journal of Software, vol. 10(8), pp. 2535-2540, 2013. [8] E. Kavallieratou, E. Stamatatos, N. Fakotakis and G. Kokkinakis, "Handwritten character segmentation using transformation-based learning," Proceedings 15th International Conference on Pattern Recognition. ICPR2000, vol.2, pp. 634-637, 2000. [9] R. Ghosh, "Stroke segmentation of online handwritten word using the busy zone concept," 2013 International Conference on Soft Computing and Pattern Recognition (SoCPaR), pp. 54-59, 2013. [10] F. Naohiro, J. Tokuno and H. Ikeda, "Online character segmentation method for unconstrained handwriting strings using off-stroke features," Tenth International Workshop on Frontiers in Handwriting Recognition, IWFHR-10, pp. 361-366, 2006. [11] N. Bhattacharya and U. Pal, "Stroke segmentation and recognition from Bangla online handwritten text," 2012 International Conference on Frontiers in Handwriting Recognition, pp. 740-745, 2012. [12] I. Mayire, H. Askar, T. Dilmurat, "A dynamic programming method for segmentation of online cursive Uyghur handwritten words into basic recognizable units," Journal of Software, vol. 8 (10), pp. 2535-2540, 2013. [13] A. Graves and J. Schmidhuber, "Framewise phoneme classification with bidirectional LSTM and other neural network architectures," Neural Networks, v.18 n.5-6, pp. 602-610, 2005. [14] A. Graves, M. Liwicki, S. Fernndez, R. Bertolami, H. Bunke and J. Schmidhuber, "A novel connectionist system for unconstrained handwriting recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31 (5), pp. 855-868, 2009. [15] A. Graves, "RNNLIB: A recurrent neural network library for sequence learning problems," http://sourceforge.net/projects/rnnl/, 2013. [16] E. Indermhle, M. Liwicki and H. Bunke, "IAMonDo-database: an online handwritten document database with non-uniform contents," In Proc. Of Int. Workshop on Document Analysis Systems, pp. 97-104, 2010. [17] S. J. Young, N. H. Russell, and J. H. S. Thornton, "Token passing: A simple conceptual model for connected speech recognition systems," Tech. Rep. CUED/F-INFENG/TR38, Cambridge University Engineering Department, 1989. [18] F. Chunsheng, "From Dynamic Time Warping (DTW) to Hidden Markov Model (HMM) Final project report for ECE742 Stochastic Decision," 2009. [19] V. Khomenko, O. Shyshkov, O. Radyvonenko and K. Bokhan, "Accelerating recurrent neural network training using sequence bucketing and multi-GPU data parallelization," Proceedings of the 2016 IEEE First International Conference on Data Stream Mining & Processing, pp. 100-103, 2016. |
| Content type: | Conference Abstract |
| Appears in Collections: | Data stream mining and processing : proceedings of the IEEE second international conference |
| File | Description | Size | Format | |
|---|---|---|---|---|
| 2018_Volkova_V-Improvement_of_Character_218-222.pdf | 307.4 kB | Adobe PDF | View/Open | |
| 2018_Volkova_V-Improvement_of_Character_218-222__COVER.png | 491.96 kB | image/png | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.