Chinese Handwriting Identification Method Based on Keyword Extraction

Text-independent handwriting identification methods require that features such as texture are extracted from lengthy document image; while text-dependent handwriting identification methods require that the contents of the documents being compared are identical. In order to overcome these confinements, this paper presents a novel Chinese handwriting identification technique. First, Chinese characters are segmented from handwriting document, then keywords are extracted based on matching and voting of local features of character. Then the same-content keywords are used to build training sets, and these training sets of two documents are compared. Because the keywords are similar to signature, the handwriting identification problem is transformed into signature verification problem. Experiments on HIT-MW, HIT-SW and CASIA show this method outperforms many text-independent handwriting identification methods.

[1]  Siti Mariyam Shamsuddin,et al.  Writer Identification for Chinese Handwriting , 2010, SOCO 2010.

[2]  Xin Li,et al.  A Microstructure Feature Based Text-independent Method of Writer Identification for Multilingual Handwritings: A Microstructure Feature Based Text-independent Method of Writer Identification for Multilingual Handwritings , 2009 .

[3]  HU Sheng-xiong.  Handwriting Identification Based on Magnitude and Relative Phase Information , 2011 .

[4]  Ding Xiaoqing.  Writer identification based on improved microstructure features , 2010 .

[5]  Yuan Yan Tang,et al.  Thinning Character Using Modulus Minima of Wavelet Transform , 2006, Int. J. Pattern Recognit. Artif. Intell..

[6]  Zhenyu He,et al.  Writer identification of Chinese handwriting documents using hidden Markov tree model , 2008, Pattern Recognit..

[7]  S. Mahmoud,et al.  State of the art in off-line writer identification of handwritten text and survey of writer identification of Arabic text , 2012 .

[8]  Chang-Dong Wang,et al.  A Stroke Shape and Structure Based Approach for Off-line Chinese Handwriting Identification , 2011 .

[9]  Xinge You,et al.  Kernel Learning for Dynamic Texture Synthesis , 2016, IEEE Transactions on Image Processing.

[10]  Jiang Yu-ming.  Algorithm for offline handwritten Chinese character segmentation based on stroke bounding box , 2005 .

[11]  Sebastian Kummer,et al.  Designing and Decision Making of Transport Chains between China and Germany , 2010 .

[12]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[13]  Sun Lin-juan.  Image segmentation algorithm of single handwritten Chinese characters , 2010 .

[14]  Chafic Mokbel,et al.  Dynamic and Contextual Information in HMM Modeling for Handwritten Word Recognition , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Alicia Fornés,et al.  Rotation invariant hand-drawn symbol recognition based on a dynamic time warping model , 2010, International Journal on Document Analysis and Recognition (IJDAR).

[16]  Liu Hai.  Text-independent Writer Identification of Offline Chinese Handwriting Using Contour-directional Feature , 2011 .

[17]  Yang Jing-yu.  An Effective Multi-stage Segmentation Method for Handwritten Chinese Characters , 2007 .

[18]  Giuseppe Iaria,et al.  Encoding in the Visual Word Form Area: An fMRI Adaptation Study of Words versus Handwriting , 2010, Journal of Cognitive Neuroscience.

[19]  Jing Huang,et al.  Rotation invariant iris feature extraction using Gaussian Markov random fields with non-separable wavelet , 2010, Neurocomputing.

[20]  Li Wen.  Automatic detection of OPCCR errors based on mesh grid density features of strokes , 2011 .

[21]  Jesús Francisco Vargas-Bonilla,et al.  Off-line signature verification based on grey level information using texture features , 2011, Pattern Recognit..