A Character Based Handwritten Identification Using Neural Network and SVM

Authors

  • Rohitash Kumar  Guru Kashi University, Talwandi Sabo, Bathinda, Punjab, India
  • Mandeep Kaur  Guru Kashi University, Talwandi Sabo, Bathinda, Punjab, India

Keywords:

PCA, SVM, MATLAB, DEF, PCA, LDA, IAM, ICDAR, GUI, CCR, PSNR

Abstract

Handwritten identification is carried out using handwritten text. The Research work on investigates highly discriminating features for handwritten identification for off-line handwritten multiple text lines and passages. Five categories of features are tested: slant and slant energy, skew, pixel distribution, curvature, and entropy. These features support high recognition rates and are competitive with other state of the art methods for handwritten identification. The directional element features are first extracted from the handwriting character scripts, then the dimensions of the features is reduced using PCA in order to cope with the small sample size problem. The most discriminative features are extracted from the reduced feature space using Fisher's Linear Discriminant Analysis. The Euclidian distance is Research for classification. Experimental result using SVM and NN verified the effectiveness of the Research work. For the implementation of this Research work we use the Image Processing Toolbox under MATLAB software.

References

  1. Zachary A. Daniels and Henry S. Baird," Discriminating Features for Handwritten Identification". In the Document Analysis and Recognition (ICDAR ),2014 .International Conference on,pages 1417-1421 ,IEEE 2014.
  2. Bensefia, A. Nosary, T. Paquet, and L. Heutte," Handwritten identification by writer’s invariants", International Workshop on Frontiers in Handwriting Recognition, pages 274–279, 2002.
  3. Bensefia, T. Paquet, and L. Heutte, "Information retrieval based Handwritten identification" In Seventh Int. Conf. on Document Analysis and Recognition, pages 946–950, 2003.
  4. Louloudis, B.Gatos, N.Stamatopoulos and A.Papandreou,"ICDAR2013 Competition on Handwritten Identification" In the Document Analysis and Recognition (ICDAR ),2013 .International Conference on,pages 1429-1432 ,IEEE 2013
  5. Bulacu, L. Schomaker, and L. Vuurpijl, " Handwritten identification using edge-based directional features", In Seventh International Conference on Document Analysis and Recognition, pages 937–941, 2003.
  6. Bunke, " Recognition of cursive roman handwriting – past, present and future", Seventh International. Conference on Document Analysis and Recognition, pages 448–461, 2003.
  7. H. Cha and S. Srihari, "Multiple feature integration for Handwritten verification"In L. Schomaker and L. Vuurpijl, editors, Proc. Seventh International Workshop on Frontiers in Handwriting Recognition, pages 333–342, 2000.
  8. Hertel and H. Bunke., "A set of novel features for Handwritten identification", In J. Kittler and M. Nixon, editors, Audio and Video-Based Biometric Person Authentication, pages 679– 687, 2003.
  9. Leclerc and R. Plamondon, " Automatic signature verification: The state of the art 1989–1993", In R. Plamondon, editor, Progress in Automatic Signature Verification, pages 13–19. World Scientific Publ. Co., 1994.
  10. Leedham and S. Chachra, "Writer identification using innovative binarised features of handwritten numerals",In Seventh International Conference on Document Analysis and Recognition, pages 413–417, 2003.
  11. V. Marti and H. Bunke, "Using a statistical language model to improve the performance of an HMM-based cursive handwriting recognition system", International Journal of Pattern Recognition and Artificial Intelligence, 15:65–90, 2001.
  12. V. Marti and H. Bunke. " The IAM–database: An English sentence database for off-line handwriting recognition", International Journal of Document Analysis and Recognition, 5:39–46, 2002.
  13. Marukatat, T. Arti`eres, P. Gallinari, and B. Dorizzi "Rejection measures for handwriting sentence recognition" In Proc. of the Eighth International Conference on Frontiers in Handwriting Recognition, pages 25–29, 2002.
  14. Nosary, L. Heutte, T. Paquet, and Y. Lecourtier, " Defining writer’s invariants to adapt the recognition task" ,In Fifth International Conference on Document Analysis and Recognition, pages 765–768, 1999.
  15. Plamondon and G. Lorette, " Automatic signature verification and Handwritten identification – the state of the art",In Pattern Recognition, volume 22, pages 107–131, 1989.
  16. Plamondon and S. Srihari, "On-line and off-line handwriting recognition: A comprehensive survey" , IEEE Trans. on Pattern Analysis and Machine Intelligence, 22:63–84, 2000.
  17. R. Rabiner, "A tutorial on hidden Markov models and selected applications in speech recognition", Proc. of the IEEE, 77(2):257–285, 1989.
  18. E. Rosenberg, J. Delong, C. H. Huang, and F. K. Soong, "The use of cohort normalized scores for speaker verification", Proceeding International. Conference on Spoken Language Processing, pages 599–602, 1992.
  19. E. S. Said, T. Tan, and K. Baker, "Personal identification based on handwriting", Pattern Recognition, 33:149– 160, Jan. 2000.
  20. Schlapbach and H. Bunke, "Off-line handwriting identification using HMM based recognizers", Accepted for publication in Proc. 17th International Conference on Pattern Recognition, 2004.
  21. Young, G. Evermann, D. Kershaw, G. Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev, and P. Woodland. "The HTK book", 2002.
  22. N. Zois and V. Anastassopoulos, " Morphological waveform coding for Handwritten identification", Pattern Recognition, 33:385–398, Mar. 2000.
  23. S.N. Srihari, S.H. Cha, H. Arora, and S. Lee, "Individuality of handwriting: a validation study", In Document Analysis and Recognition, 2001. Proceedings, Sixth International Conference on, pages 106–109. IEEE, 2001.

International Journal of Scientific Research in Science, Engineering and Technology

Downloads

Published

2017-02-28

Issue

Volume 3, Issue 1, January-February-2017

Section

Research Articles

License

Copyright (c) IJSRSET

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
Rohitash Kumar, Mandeep Kaur, " A Character Based Handwritten Identification Using Neural Network and SVM, International Journal of Scientific Research in Science, Engineering and Technology(IJSRSET), Print ISSN : 2395-1990, Online ISSN : 2394-4099, Volume 3, Issue 1, pp.120-124, January-February-2017.