Document AnalysisNo Access

Chinese Handwriting Identification Method Based on Keyword Extraction

Rui Chen

College of Computer Science, Chongqing University, Chongqing 400044, P. R. China

Search for more papers by this author

Bin Fang

College of Computer Science, Chongqing University, Chongqing 400044, P. R. China

E-mail Address: fb@cqu.edu.cn

Corresponding author.

Search for more papers by this author

, and

Patrick Shen-Pei Wang

College of Computer and Information Science, Northeastern University, Boston, MA 02115, USA

Search for more papers by this author

https://doi.org/10.1142/S0218001417530044Cited by:2 (Source: Crossref)

Abstract

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.

Keywords:

References

1. S. M. Awaida and S. A. Mahmoud, State of the art in off-line writer identification of handwritten text and survey of writer identification of Arabic text, Educ. Res. Rev. 7 (20) (2012) 445–463. Crossref, Google Scholar
2. J. Barton, C. Fox, A. Sekunova and G. Iaria, Encoding in the visual word form area: An fMRI adaptation study of words versus handwriting, J. Cogn. Neurosci. 22 (8) (2010) 1649–1661. Crossref, Web of Science, Google Scholar
3. S. Belongie, J. Malik and J. Puzicha, Shape matching and object recognition using shape contexts, IEEE Trans. Pattern Anal. Mach. Intell. 24 (4) (2002) 509–522. Crossref, Web of Science, Google Scholar
4. A. L. Biannebernard, F. Menasri, M. R. Alhajj et al., Dynamic and contextual information in HMM modeling for handwritten word recognition, IEEE Trans. Pattern Anal. Mach. Intell. 33 (10) (2011) 2066–2080. Crossref, Web of Science, Google Scholar
5. G. Chen, B. C. Li and C. Wen, Effective off-line signature recognition method based on evidence theory, Comput. Eng. Des. 27 (17) (2006) 3256–3260. Google Scholar
6. X. Chen, M. Zhu and Y. Zhong, HTM based offline signature recognition and improvement, J. Sichuan Univ. 43 (1) (2011) 146–150. Google Scholar
7. L. Cheng, An approach of handwriting identification based on wavelet an analysis and fractal dimension, J. Xichang Coll. 25 (1) (2011) 35–39. Google Scholar
8. A. Forns, J. Llads, G. Snchez and D. Karatzas, Rotation invariant hand-drawn symbol recognition based on a dynamic time warping model, Int. J. Doc. Anal. Recognit. 13 (3) (2010) 229–241. Crossref, Web of Science, Google Scholar
9. B. Gu, X. Y. Liu and S. S. Li, Recognizing the pen trajectories of static signatures using hidden markov model, Comput. Digital Eng. 35 (10) (2007) 70–72. Google Scholar
10. Z. Y. He, X. G. You and Y. Y. Tang, Writer identification of Chinese handwriting documents using hidden Markov tree model, Pattern Recognit. 41 (4) (2008) 1295–1307. Crossref, Web of Science, Google Scholar
11. J. Huang, X. You and Y. Y. Tang, Rotation invariant iris feature extraction using Gaussian Markov random fields with non-separable wavelet, Neurocomputing 73 (4–6) (2010) 883–894. Crossref, Web of Science, Google Scholar
12. W. Y. Leng and S. M. Shamsuddin, Writer identification for Chinese handwriting, Int. J. Soft Comput. Appl. 2 (2) (2010) 160–173. Google Scholar
13. W. L. Li, Z. W. Shang and L. F. Zhang, Handwriting identification based on magnitude and relative phase information, Comput. Eng. 37 (13) (2011) 33–39. Google Scholar
14. X. Li and X. Q. Ding, Writer identification based on improved microstructure features, J. Tsinghua Univ. 50 (4) (2010) 595–600. Google Scholar
15. X. Li, X. Q. Ding and L. R. Peng, A microstructure feature based text-independent method of writer identification for multilingual handwritings, Acta Autom. Sin. 35 (9) (2009) 1199–1208. Crossref, Google Scholar
16. H. Liu and Y. Lu, Text-independent writer identification of offline chinese handwriting using contour-directional feature, Video Appl. Proj. 35 (21) (2011) 131–144. Google Scholar
17. H. Liu, Y. M. Yu and D. S. Luo, English character recognition based on momentum BP neural network, J. Sichuan Univ. 48 (6) (2011) 1324–1328. Google Scholar
18. R. Ma and J. Y. Yang, An effective multi-stage segmentation method for handwritten chinese characters, J. Image Graphics 12 (11) (2007) 2062–2067. Google Scholar
19. J. Tan, J. H. Lai and C. D. Wang, A stroke shape and structure based approach for off-line Chinese handwriting identification, Int. J. Intell. Syst. Appl. 2 (2) (2011) 1–8. Google Scholar
20. J. F. Vargas, Off-line signature verification based on grey level information using texture features, Pattern Recognit. 44 (2) (2011) 375–385. Crossref, Web of Science, Google Scholar
21. H. Z. Wang and Y. M. Jiang, Algorithm for offline handwritten Chinese character segmentation based on stroke bounding box, Comput. Eng. Des. 26 (3) (2005) 803–306. Google Scholar
22. J. Wen and J. L. Chen, Text-independent writer identification of offline Chinese handwriting using contour-directional feature, Comput. Eng. Applic. 47 (36) (2011) 180–182. Google Scholar
23. Y. Yi, W. B. Li, J. Zhang and L. D. Sheng, Automatic detection of OPCCR errors based on mesh grid density features of strokes, J. Sichuan Univ. 48 (6) (2011) 1353–1358. Google Scholar
24. X. You, Q. Chen, B. Fang and Y. Y. Tang, Thinning character using modulus minima of wavelet transform, Int. J. Pattern Recognit. Artif. Intell. 20 (3) (2006) 361–375. Link, Web of Science, Google Scholar
25. X. You, W. Guo, S. Yu, K. Li, J. C. Prncipe and D. Tao, Kernel learning for dynamic texture synthesis, IEEE Trans. Image Process. 25 (10) (2016) 4782–4795. Crossref, Web of Science, Google Scholar
26. M. Yu, Y. Y. Zhang and C. H. Xue, Image segmentation algorithm of single handwritten Chinese characters, Comput. Eng. Appl. 46 (9) (2010) 180–182. Google Scholar
27. L. Zhang, L. B. Cheng, Off-line signature recognition based on multi-features and evidence theory, Comput. Eng. Appl. 43 (8) (2007) 234–237. Google Scholar
28. Z. Y. Zhao, Z. X. Yang, Z. Y. Li and W. Luo, Handwriting identification based on texture character, Control Autom. 26 (2) (2010) 205–207. Google Scholar