A character image restoration method for unconstrained handwritten Chinese character recognition

Despite the success of methods on constrained handwriting databases, recognition of unconstrained handwritten Chinese characters remains a big challenge. One difficulty for recognizing unconstrained handwritting is that some connected strokes are involved or some strokes are omitted. In this paper, a character image restoration method is proposed for unconstrained handwritten Chinese character recognition. In this method, the observed character image is modeled as the combination of the ideal character image with two types of noise images: the omitted stroke noise image and the added stroke noise image. To preserve the original gradient features, restoration is done on the gradient features. The estimated features are then used to discriminate similar characters. To show the effectiveness of the proposed method, we extend some state-of-the-art classifiers based on the estimated features. Experimental results show that the extended classifiers outperform the original state-of-the-art classifiers. This demonstrates that the estimated features are useful for further improving the recognition rate.

[1]  Hiromichi Fujisawa,et al.  Machine Learning in Document Analysis and Recognition , 2008, Studies in Computational Intelligence.

[2]  Hiromitsu Yamada,et al.  A nonlinear normalization method for handprinted kanji character recognition - line density equalization , 1990, Pattern Recognit..

[3]  Yoshiyuki Yamashita,et al.  Classification of handprinted Kanji characters by the structured segment matching method , 1983, Pattern Recognit. Lett..

[4]  Fei Yin,et al.  Online and offline handwritten Chinese character recognition: Benchmarking on new databases , 2013, Pattern Recognit..

[5]  Cheng-Lin Liu,et al.  Handwritten Chinese Character Recognition: Effects of Shape Normalization and Feature Extraction , 2006, SACH.

[6]  Cheng-Lin Liu,et al.  Normalization-Cooperated Gradient Feature Extraction for Handwritten Character Recognition , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[8]  Jürgen Schmidhuber,et al.  Multi-column deep neural networks for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Hiroshi Sako,et al.  Handwritten Chinese character recognition: alternatives to nonlinear normalization , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[10]  Fumitaka Kimura,et al.  Modified Quadratic Discriminant Functions and the Application to Chinese Character Recognition , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  J. Tsukumo,et al.  Classification of handprinted Chinese characters using nonlinear normalization and correlation methods , 1988, [1988 Proceedings] 9th International Conference on Pattern Recognition.

[12]  James Joseph Biundo,et al.  Analysis of Contingency Tables , 1969 .

[13]  In-Jung Kim,et al.  Discrimination of similar characters using nonlinear normalization based on regional importance measure , 2013, International Journal on Document Analysis and Recognition (IJDAR).

[14]  Cheng-Lin Liu,et al.  High accuracy handwritten Chinese character recognition using LDA-based compound distances , 2008, Pattern Recognit..

[15]  G. W. Snedecor.  Statistical Methods , 1964 .

[16]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[17]  Meng Shi,et al.  Handwritten numeral recognition using gradient and curvature of gray scale image , 2002, Pattern Recognit..

[18]  Cheng-Lin Liu,et al.  Classification and Learning Methods for Character Recognition: Advances and Remaining Problems , 2008, Machine Learning in Document Analysis and Recognition.

[19]  Cheng-Lin Liu,et al.  Pseudo two-dimensional shape normalization methods for handwritten Chinese character recognition , 2005, Pattern Recognit..

[20]  Yunxue Shao,et al.  Fast self-generation voting for handwritten Chinese character recognition , 2012, International Journal on Document Analysis and Recognition (IJDAR).

[21]  Takahiko Kawatani.  Handwritten Kanji recognition with determinant normalized quadratic discriminant function , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[22]  Hiroshi Sako,et al.  Handwritten digit recognition: investigation of normalization and feature extraction techniques , 2004, Pattern Recognit..

[23]  Cheng-Lin Liu,et al.  LDA-Based Compound Distance for Handwritten Chinese Character Recognition , 2007 .

[24]  R. Casey.  Moment normalization of handprinted characters , 1970 .

[25]  Cheng-Lin Liu,et al.  High Accuracy Handwritten Chinese Character Recognition Using Quadratic Classifiers with Discriminative Feature Extraction , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[26]  Cheng-Lin Liu,et al.  Evaluation of weighted Fisher criteria for large category dimensionality reduction in application to Chinese handwriting recognition , 2013, Pattern Recognit..

[27]  Sargur N. Srihari,et al.  Gradient-based contour encoding for character recognition , 1996, Pattern Recognit..

[28]  Xiaobo Jin,et al.  Regularized margin-based conditional log-likelihood loss for prototype learning , 2010, Pattern Recognit..

[29]  Ka-Chung Leung,et al.  Recognition of Handwritten Chinese Characters by Combining Regularization, Fisher's Discriminant and Distorted Sample Generation , 2009, 2009 10th International Conference on Document Analysis and Recognition.

[30]  Cheng-Lin Liu,et al.  Building compact classifier for large character set recognition using discriminative feature extraction , 2005, Eighth International Conference on Document Analysis and Recognition (ICDAR'05).

[31]  Bo Xu,et al.  Similar Handwritten Chinese Characters Recognition by Critical Region Selection Based on Average Symmetric Uncertainty , 2010, 2010 12th International Conference on Frontiers in Handwriting Recognition.

[32]  Seong-Whan Lee,et al.  Performance evaluation of nonlinear shape normalization methods for the recognition of large-set handwritten characters , 1993, Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93).

[33]  Multiple Instance Learning Based Method for Similar Handwritten Chinese Characters Discrimination , 2011, 2011 International Conference on Document Analysis and Recognition.

[34]  Nei Kato,et al.  A Handwritten Character Recognition System Using Directional Element Feature and Asymmetric Mahalanobis Distance , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[35]  Ka-Chung Leung,et al.  Recognition of handwritten Chinese characters by critical region analysis , 2010, Pattern Recognit..

[36]  Hiroshi Sako,et al.  Performance evaluation of pattern classifiers for handwritten character recognition , 2002, International Journal on Document Analysis and Recognition.

[37]  Stefan Jäger,et al.  Arabic and Chinese Handwriting Recognition - SACH 2006 Summit College Park, MD, USA, September 27-28, 2006 Selected Papers , 2008, SACH.

[38]  Fei Yin,et al.  CASIA Online and Offline Chinese Handwriting Databases , 2011, 2011 International Conference on Document Analysis and Recognition.

[39]  Tetsushi Wakabayashi,et al.  Improvement of handwritten Japanese character recognition using weighted direction code histogram , 1997, Pattern Recognit..

[40]  Ryoji Haruki,et al.  Two-dimensional extension of nonlinear normalization method using line density for character recognition , 1997, Proceedings of the Fourth International Conference on Document Analysis and Recognition.

[41]  Anil K. Jain,et al.  Feature extraction methods for character recognition-A survey , 1996, Pattern Recognit..

[42]  Lianwen Jin,et al.  A comparative study of gabor feature and gradient feature for handwritten chinese character recognition , 2007, 2007 International Conference on Wavelet Analysis and Pattern Recognition.