The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.07 - July (2013 vol.35)
pp: 1773-1787
Xu-Yao Zhang , Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China
Cheng-Lin Liu , Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China
ABSTRACT
Adapting a writer-independent classifier toward the unique handwriting style of a particular writer has the potential to significantly increase accuracy for personalized handwriting recognition. This paper proposes a novel framework of style transfer mapping (STM) for writer adaptation. The STM is a writer-specific class-independent feature transformation which has a closed-form solution. After style transfer mapping, the data of different writers are projected onto a style-free space, where the writer-independent classifier needs no change to classify the transformed data and can achieve significantly higher accuracy. The framework of STM can be combined with different types of classifiers for supervised, unsupervised, and semi-supervised adaptation, where writer-specific data can be either labeled or unlabeled and need not cover all classes. In this paper, we combine STM with the state-of-the-art classifiers for large-category Chinese handwriting recognition: learning vector quantization (LVQ) and modified quadratic discriminant function (MQDF). Experiments on the online Chinese handwriting database CASIA-OLHWDB demonstrate that STM-based adaptation is very efficient and effective in improving classification accuracy. Semi-supervised adaptation achieves the best performance, while unsupervised adaptation is even better than supervised adaptation. On handwritten text data, semi-supervised adaptation achieves error reduction rates 31.95 and 25.00 percent by LVQ and MQDF, respectively.
INDEX TERMS
Prototypes, Hidden Markov models, Handwriting recognition, Accuracy, Adaptation models, Training, Context,handwriting recognition, Writer adaptation, style transfer mapping
CITATION
Xu-Yao Zhang, Cheng-Lin Liu, "Writer Adaptation with Style Transfer Mapping", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.35, no. 7, pp. 1773-1787, July 2013, doi:10.1109/TPAMI.2012.239
REFERENCES
[1] C. Leggetter and P. Woodland, "Maximum Likelihood Linear Regression for Speaker Adaptation of Continuous Density Hidden Markov Models," Computer Speech and Language, vol. 9, no. 2, pp. 171-185, 1995.
[2] H. DauméIII and D. Marcu, "Domain Adaptation for Statistical Classifiers," J. Artificial Intelligence Research, vol. 26, pp. 101-126, 2006.
[3] R. Caruana, "Multitask Learning," Machine Learning, vol. 28, no. 1, pp. 41-75, 1997.
[4] S.J. Pan and Q. Yang, "A Survey on Transfer Learning," IEEE Trans. Knowledge and Data Eng., vol. 22, no. 10, pp. 1345-1359, Oct. 2010.
[5] M. Kelly, D. Hand, and N. Adams, "The Impact of Changing Populations on Classifier Performance," Proc. ACM Int'l Conf. Knowledge Discovery and Data Mining, pp. 367-371, 1999.
[6] T. Kohonen, "The Self-Organizing Map," Proc. IEEE, vol. 78, no. 9, pp. 1464-1480, Sept. 1990.
[7] A. Sato and K. Yamada, "Generalized Learning Vector Quantization," Proc. Advances in Neural Information Processing Systems Conf., pp. 423-429, 1996.
[8] F. Kimura, K. Takashina, S. Tsuruoka, and Y. Miyake, "Modified Quadratic Discriminant Functions and the Application to Chinese Character Recognition," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 9, no. 1, pp. 149-153, Jan. 1987.
[9] C.-L. Liu, F. Yin, D.-H. Wang, and Q.-F. Wang, "CASIA Online and Offline Chinese Handwriting Databases," Proc. Int'l Conf. Document Analysis and Recognition, pp. 37-41, 2011.
[10] X.-Y. Zhang and C.-L. Liu, "Style Transfer Matrix Learning for Writer Adaptation," Proc. IEEE Int'l Conf. Computer Vision and Pattern Recognition, pp. 393-400, 2011.
[11] N. Matic, I. Guyon, J. Denker, and V. Vapnik, "Writer-Adaptation for On-Line Handwritten Character Recognition," Proc. Int'l Conf. Document Analysis and Recognition, pp. 187-191, 1993.
[12] J. Platt and N. Matic, "A Constructive RBF Network for Writer Adaptation," Proc. Advances in Neural Information Processing Systems Conf., 1997.
[13] L. Haddad, T. Hamdani, M. Kherallah, and A. Alimi, "Improvement of On-Line Recognition Systems Using a RBF-Neural Network Based Writer Adaptation Module," Proc. Int'l Conf. Document Analysis and Recognition, pp. 284-288, 2011.
[14] W. Kienzle and K. Chellapilla, "Personalized Handwriting Recognition via Biased Regularization," Proc. Int'l Conf. Machine Learning, pp. 457-464, 2006.
[15] N. Tewari and A. Namboodiri, "Learning and Adaptation for Improving Handwritten Character Recognizers," Proc. Int'l Conf. Document Analysis and Recognition, pp. 86-90, 2009.
[16] V. Vuori and T. Korkeakoulu, "Adaptive Methods for Online Recognition of Isolated Handwritten Characters," Helsinki Univ. of Tech nology, 2002.
[17] H. Mouchère, E. Anquetil, and N. Ragot, "Writer Style Adaptation in On-Line Handwriting Recognizers by a Fuzzy Mechanism Approach: The ADAPT Method," Int'l J. Pattern Recognition and Artificial Intelligence, vol. 21, no. 1, pp. 99-116, 2007.
[18] H. Takebe, K. Kurokawa, Y. Katsuyama, and S. Naoi, "A Learning Pseudo Bayes Discriminant Method Based on Difference Distribution of Feature Vectors," Proc. Int'l Workshop Document Analysis Systems, pp. 134-144, 2002.
[19] K. Ding and L. Jin, "Incremental MQDF Learning for Writer Adaptive Handwriting Recognition," Proc. Int'l Conf. Frontiers in Handwriting Recognition, pp. 559-564, 2010.
[20] J. LaViola and R. Zeleznik, "A Practical Approach for Writer-Dependent Symbol Recognition Using a Writer-Independent Symbol Recognizer," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 29, no. 11, pp. 1917-1926, Nov. 2007.
[21] M. Aksela and J. Laaksonen, "Adaptive Combination of Adaptive Classifiers for Handwritten Character Recognition," Pattern Recognition Letters, vol. 28, no. 1, pp. 136-143, 2007.
[22] S.D. Connell and A.K. Jain, "Writer Adaptation for Online Handwriting Recognition," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 3, pp. 329-346, Mar. 2002.
[23] K. Chellapilla, P. Simard, and A. Abdulkader, "Allograph Based Writer Adaptation for Handwritten Character Recognition," Proc. Int'l Workshop Frontiers in Handwriting Recognition, pp. 423-428, 2006.
[24] M. Szummer and C. Bishop, "Discriminative Writer Adaptation," Proc. Int'l Workshop Frontiers in Handwriting Recognition, 2006.
[25] H. Cao, R. Prasad, S. Saleem, and P. Natarajan, "Unsupervised HMM Adaptation Using Page Style Clustering," Proc. Int'l Conf. Document Analysis and Recognition, pp. 1091-1095, 2009.
[26] A. Brakensiek, A. Kosmala, and G. Rigoll, "Comparing Adaptation Techniques for On-Line Handwriting Recognition," Proc. Int'l Conf. Document Analysis and Recognition, pp. 486-490, 2001.
[27] A. Vinciarelli and S. Bengio, "Writer Adaptation Techniques in HMM Based Off-Line Cursive Script Recognition," Pattern Recognition Letters, vol. 23, no. 8, pp. 905-916, 2002.
[28] L. Jin, K. Ding, and Z. Huang, "Incremental Learning of LDA Model for Chinese Writer Adaptation," Neurocomputing, vol. 73, no. 10, pp. 1614-1623, 2010.
[29] Z. Huang, K. Ding, L. Jin, and X. Gao, "Writer Adaptive Online Handwriting Recognition Using Incremental Linear Discriminant Analysis," Proc. Int'l Conf. Document Analysis and Recognition, pp. 91-95, 2009.
[30] G. Nagy and G. SheltonJr., "Self-Corrective Character Recognition System," IEEE Trans. Information Theory, vol. 12, no. 2, pp. 215-222, 1966.
[31] S. Veeramachaneni and G. Nagy, "Analytical Results on Style-Constrained Bayesian Classification of Pattern Fields," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 29, no. 7, pp. 1280-1285, July 2007.
[32] P. Sarkar and G. Nagy, "Style Consistent Classification of Isogenous Patterns," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 27, no. 1, pp. 88-98, Jan. 2005.
[33] S. Veeramachaneni and G. Nagy, "Style Context with Second-Order Statistics," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 27, no. 1, pp. 14-22, Jan. 2005.
[34] S. Veeramachaneni and G. Nagy, "Adaptive Classifiers for Multisource OCR," Int'l J. Document Analysis and Recognition, vol. 6, pp. 154-166, 2003.
[35] J. Tenenbaum and W. Freeman, "Separating Style and Content with Bilinear Models," Neural Computation, vol. 12, no. 6, pp. 1247-1283, 2000.
[36] X.-Y. Zhang, K. Huang, and C.-L. Liu, "Pattern Field Classification with Style Normalized Transformation," Proc. Int'l Joint Conf. Artificial Intelligence, pp. 1621-1626, 2011.
[37] J. Rodríguez-Serrano, F. Perronnin, G. Sánchez, and J. Lladós, "Unsupervised Writer Adaptation of Whole-Word HMMs with Application to Word-Spotting," Pattern Recognition Letters, vol. 31, no. 8, pp. 742-749, 2010.
[38] A. Nosary, L. Heutte, and T. Paquet, "Unsupervised Writer Adaptation Applied to Handwritten Text Recognition," Pattern Recognition, vol. 37, no. 2, pp. 385-388, 2004.
[39] G. Huang, A. Kae, C. Doersch, and E. Learned-Miller, "Bounding the Probability of Error for High Precision Optical Character Recognition," J. Machine Learning Research, vol. 12, pp. 363-387, 2012.
[40] P. Xiu and H. Baird, "Whole-Book Recognition," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 34, no. 12, pp. 2467-2480, Dec. 2012.
[41] V. Frinken and H. Bunke, "Evaluating Retraining Rules for Semi-Supervised Learning in Neural Network Based Cursive Word Recognition," Proc. Int'l Conf. Document Analysis and Recognition, pp. 31-35, 2009.
[42] A. Blum and T. Mitchell, "Combining Labeled and Unlabeled Data with Co-Training," Proc. Ann. Conf. Computational Learning Theory, pp. 92-100, 1998.
[43] S. Goldman and Y. Zhou, "Enhancing Supervised Learning with Unlabeled Data," Proc. Int'l Conf. Machine Learning, pp. 327-334, 2000.
[44] V. Frinken, A. Fischer, H. Bunke, and A. Foornes, "Co-Training for Handwritten Word Recognition," Proc. Int'l Conf. Document Analysis and Recognition, pp. 314-318, 2011.
[45] L. Oudot, L. Prevost, and M. Milgram, "Self-Supervised Adaptation for On-Line Script Text Recognition," Electronic Letters on Computer Vision and Image Analysis, vol. 5, no. 2, pp. 87-97, 2005.
[46] G. Ball and S. Srihari, "Prototype Integration in Off-Line Handwriting Recognition Adaptation," Proc. Int'l Conf. Frontiers in Handwriting Recognition, pp. 529-534, 2008.
[47] G. Ball and S. Srihari, "Semi-Supervised Learning for Handwriting Recognition," Proc. Int'l Conf. Document Analysis and Recognition, pp. 26-30, 2009.
[48] S. Vajda, A. Junaidi, and G. Fink, "A Semi-Supervised Ensemble Learning Approach for Character Labeling with Minimal Human Effort," Proc. Int'l Conf. Document Analysis and Recognition, pp. 259-263, 2011.
[49] A. Arora and A. Namboodiri, "A Semi-Supervised SVM Framework for Character Recognition," Proc. Int'l Conf. Document Analysis and Recognition, pp. 1105-1109, 2011.
[50] C.-L. Liu and M. Nakagawa, "Evaluation of Prototype Learning Algorithms for Nearest-Neighbor Classifier in Application to Handwritten Character Recognition," Pattern Recognition, vol. 34, no. 3, pp. 601-615, 2001.
[51] X.-B. Jin, C.-L. Liu, and X. Hou, "Regularized Margin-Based Conditional Log-Likelihood Loss for Prototype Learning," Pattern Recognition, vol. 43, no. 7, pp. 2428-2438, 2010.
[52] C.-L. Liu, H. Sako, and H. Fujisawa, "Discriminative Learning Quadratic Discriminant Function for Handwriting Recognition," IEEE Trans. Neural Networks, vol. 15, no. 2, pp. 430-444, Mar. 2004.
[53] T. Long and L. Jin, "Building Compact MQDF Classifier for Large Character Set Recognition by Subspace Distribution Sharing," Pattern Recognition, vol. 41, no. 9, pp. 2916-2925, 2008.
[54] Y. Wang and Q. Huo, "Modeling Inverse Covariance Matrices by Expansion of Tied Basis Matrices for Online Handwritten Chinese Character Recognition," Pattern Recognition, vol. 42, no. 12, pp. 3296-3302, 2009.
[55] J. Platt, "Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods," Advances in Large Margin Classifiers, vol. 10, no. 3, pp. 61-74, 1999.
[56] B. Zadrozny and C. Elkan, "Transforming Classifier Scores into Accurate Multiclass Probability Estimates," Proc. ACM Int'l Conf. Knowledge Discovery and Data Mining, pp. 694-699, 2002.
[57] C.-L. Liu and X.-D. Zhou, "Online Japanese Character Recognition Using Trajectory-Based Normalization and Direction Feature Extraction," Proc. Int'l Workshop Frontiers in Handwriting Recognition, 2006.
[58] K. Ding, G. Deng, and L. Jin, "An Investigation of Imaginary Stroke Techinique for Cursive Online Handwriting Chinese character Recognition," Proc. Int'l Conf. Document Analysis and Recognition, pp. 531-535, 2009.
[59] Q.-F. Wang, F. Yin, and C.-L. Liu, "Handwritten Chinese Text Recognition by Integrating Multiple Contexts," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 34, no. 8, pp. 1469-1481, Aug. 2012.
[60] L. Bruzzone and M. Marconcini, "Domain Adaptation Problems: A DASVM Classification Technique and a Circular Validation Strategy," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 32, no. 5, pp. 770-787, May 2010.
[61] C. Bishop, Neural Networks for Pattern Recognition. Clarendon Press Oxford, 1995.
8 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool