Document AnalysisNo Access

Multiscale Region Projection Method to Discriminate Between Printed and Handwritten Text on Registration Forms

J. Tan

School of Mathematics and Computational Science, Sun Yat-Sen University, China

Search for more papers by this author

J.-H. Lai

School of Information Science and Technology, Sun Yat-Sen University, China

Search for more papers by this author

P. Wang

School of Computer and Information Science, Northeastern University, USA

Search for more papers by this author

, and

N. Bi

School of Mathematics and Computational Science, Sun Yat-Sen University, China

E-mail Address: mcsbn@mail.sysu.edu.cn

Search for more papers by this author

https://doi.org/10.1142/S0218001415530055Cited by:5 (Source: Crossref)

Abstract

Techniques to identify printed and handwritten text in scanned documents differ significantly. In this paper, we address the question of how to discriminate between each type of writing on registration forms. Registration-form documents consist of various type zones, such as printed text, handwriting, table, image, noise, etc., so segmenting the various zones is a challenge. We adopt herein an approach called “multiscale-region projection” to identify printed text and handwriting. An important aspect of our approach is the use of multiscale techniques to segment document images. A new set of projection features extracted from each zone is also proposed. The classification rules are mining and are used to discern printed text and table lines from handwritten text. The proposed system was tested on 11118 samples in two registration-form-image databases. Some possible measures of efficiency are computed, and in each case the proposed approach performs better than traditional methods.

Keywords:

References

1. J. Banerjee, A. M Namboodiri and C. V. Jawahar, Contextual restoration of severely degraded document images, IEEE Conf. Computer Vision and Pattern Recognition, 2009. CVPR 2009 (2009) 517–524. Google Scholar
2. M. Benjelil, S. Kanoun, R. Mullot and A. M. Alimi, Complex documents images segmentation based on steerable pyramid features, Int. J. Document Analysis and Recognition (IJDAR) 13 (3) (2010) 209–228. Crossref, Google Scholar
3. E. G. Birgin and M. Raydan, Robust stopping criteria for dykstra’s algorithm, SIAM J. Sci. Comput. 26 (4) (2005) 1405–1414. Crossref, Web of Science, Google Scholar
4. H. Cao and V. Govindaraju, Preprocessing of low-quality handwritten documents using markov random fields, IEEE Trans. Pattern Anal. Mach. Intell. 31 (7) (2009) 1184–1194. Crossref, Web of Science, Google Scholar
5. S. Chanda, K. Franke and U. Pal, Structural handwritten and machine print classification for sparse content and arbitrary oriented document fragments, Proc. 2010 ACM Symp. Applied Computing (2010) 18–22. Google Scholar
6. J.-L. Chen and H.-J. Lee, An efficient algorithm for form structure extraction using strip projection, Pattern Recogn. 31 (9) (1998) 1353–1368. Crossref, Web of Science, Google Scholar
7. K.-C. Fan, L.-S. Wang and Y.-T. Tu, Classification of machine-printed and handwritten texts using character block layout variance, Pattern Recogn. 31 (9) (1998) 1275–1284. Crossref, Web of Science, Google Scholar
8. F. Farooq, K. Sridharan and V. Govindaraju, Identifying handwritten text in mixed documents, ICPR (2006) 1142–1145. Google Scholar
9. J. Franke and M. Oberlander, Writing style detection by statistical combination of classifiers in form reader applications, Proc. Second Int. Conf. Document Analysis and Recognition, 1993 (1993) 581–584. Google Scholar
10. W. T. Freeman, E. C. Pasztor and O. T. Carmichael, Learning low-level vision, Int. J. Comput. Vis. 40 (1) (2000) 25–47. Crossref, Web of Science, Google Scholar
11. Y. Gao, X. Ding and C. Liu, A multi-scale text line segmentation method in freestyle handwritten documents, Proc. Sixth Int. Conf. Document Analysis and Recognition, 2001 (2001) 699–703. Google Scholar
12. M. D. Garris, Intelligent system for reading handwriting on forms, Proc. Thirty-First Hawaii Int. Conf. System Sciences, 1998 (1998) 233–242. Google Scholar
13. J. K. Guo and M. Y. Ma, Separating handwritten material from machine printed text using hidden markov models, Proc. Sixth Int. Conf. Document Analysis and Recognition, 2001 (2001) 439–443. Google Scholar
14. S.-P. Han, A successive projection method, Math. Prog. 40 (1–3) (1988) 1–14. Crossref, Web of Science, Google Scholar
15. A. Herout, M. Dubská and J. Havel, Review of hough transform for line detection, Real-Time Detection of Lines and Grids (Springer, 2013), pp. 3–16. Crossref, Google Scholar
16. F. Kaplan, A. Mazzei, P. Dillenbourg and et al., Extraction and classification of handwritten annotations, 1st Int. Workshop on Paper Computing, a Ubicomp 2010 Workshop (PaperComp 2010) (2010). Google Scholar
17. S. Kasuya and T. Umeda, Discriminator between handwritten and machine-printed characters, US Patent 4,910,787 (1990). Google Scholar
18. E. Kavallieratou, S. Stamatatos and H. Antonopoulou, Machine-printed from handwritten text discrimination, Ninth Int. Workshop on Frontiers in Handwriting Recognition, 2004. IWFHR-9 2004 (2004) 312–316. Google Scholar
19. J. Koyama, A. Hirose and M. Kato, Local-spectrum-based distinction between handwritten and machine-printed characters, 15th IEEE Int. Conf. Image Processing, 2008. ICIP 2008. (2008) 1021–1024. Google Scholar
20. K. Kuhnke, L. Simoncini and Zs. M. Kovacs-V, A system for machine-written and hand-written character distinction, Proc. Third Int. Conf. Document Analysis and Recognition, 1995 (1995) 811–814. Google Scholar
21. C.-L. Liu, M. Koga and H. Fujisawa, Gabor feature extraction for character recognition: Comparison with gradient feature, Eighth Int. Conf. Document Analysis and Recognition, 2005. Proc. (2005) 121–125. Google Scholar
22. T. Mirai and N. Kazuhide, Successive projection method for well-conditioned matrix approximation problems, IEEE Signal Process. Lett. 21 (4) (2014) 418–422. Crossref, Web of Science, Google Scholar
23. T. Nakai, K. Kise and M. Iwamura, A method of annotation extraction from paper documents using alignment based on local arrangements of feature points, Ninth Int. Conf. Document Analysis and Recognition, 2007. ICDAR 2007 (2007) 23–27. Google Scholar
24. U. Pal and B. B. Chaudhuri, Machine-printed and hand-written text lines identification, Pattern Recogn. Lett. 22 (3) (2001) 431–441. Crossref, Web of Science, Google Scholar
25. F. Pedro and H. Daniel, Efficient belief propagation for early vision, Int. J. Comput. Vis. 70 (1) (2006) 41–54. Crossref, Web of Science, Google Scholar
26. X. Peng, S. Setlur, V. Govindaraju and R. Sitaram, Handwritten text separation from annotated machine printed documents using markov random fields, Int. J. Doc. Anal. Recogn. 16 (1) (2013) 1–16. Crossref, Web of Science, Google Scholar
27. X. Peng, S. Setlur, V. Govindaraju, R. Sitaram and K. Bhuvanagiri, Markov random field based text identification from annotated machine printed documents, IEEE 10th Int. Conf. Document Analysis and Recognition, 2009. ICDAR’09. (2009). Google Scholar
28. S. J Pinson and W. A. Barrett, Connected component level discrimination of handwritten and machine-printed text using eigenfaces, 2011 Int. Conf. Document Analysis and Recognition (ICDAR) (2011) 1394–1398. Google Scholar
29. W. Postl, Method for automatic correction of character skew in the acquisition of a text original in the form of digital scan results, US Patent 4,723,297 (1988). Google Scholar
30. S. Shetty, H. Srinivasan, M. Beal and S. Srihari, Segmentation and labeling of documents using conditional random fields, Electronic Imaging 2007 (2007) 65000U. Google Scholar
31. M. S. Shirdhonkar and M. B. Kokare, Discrimination between printed and handwritten text in documents, Int. J. Comput. Appl. (2010). Google Scholar
32. S. N. Srihari, Y.-C. Shin, V. Ramanaprasad and D.-S. Lee, A system to read names and addresses on tax forms, Proc. IEEE 84 (7) (1996) 1038–1049. Crossref, Web of Science, Google Scholar
33. S. Violante, R. Smith and M. Reiss, A computationally efficient technique for discriminating between hand-written and printed text, IEE Colloquium on Document Image Processing and Multimedia Environments (1995) 1711–1717. Google Scholar
34. F. M. Wahl, K. Y. Wong and R. G. Casey, Block segmentation and text extraction in mixed text/image documents, Computer graphics and image processing 20 (4) (1982) 375–390 1982. Crossref, Google Scholar
35. S.-Y. Wang, H. S. Baird and C. An, Document content extraction using automatically discovered features, 10th Int. Conf. Document Analysis and Recognition, 2009. ICDAR’09 (2009) 1076–1080. Google Scholar
36. Y. Zheng, H. Li and D. Doermann, Machine printed text and handwriting identification in noisy document images, IEEE Trans. Pattern Anal. Mach. Intell. 26 (3) (2004) 337–353. Crossref, Web of Science, Google Scholar
37. Y. Zheng, C. Liu, X. Ding and S. Pan, Form frame line detection with directional single-connected chain, Sixth Int. Conf. Document Analysis and Recognition, 2001. Proc. (2011) 643–647. Google Scholar