Algorithms for handwritten character recognition based on constructing structural models
P.A. Khaustov

 

Tomsk Polytechnic University, Tomsk, Russia

Full text of article: Russian language.

 PDF

Abstract:
The article is devoted to the development of algorithms for handwritten character recognition based on constructing structural models. These algorithms do not require a large number of reference images for the correct functioning. Also, an approach to a thinning of the binary character representation based on the joint use of Zhang-Suen and Wu-Tsai algorithms has been proposed. The effectiveness of the proposed approach is confirmed by the results of experiments.
The article includes a detailed description of all steps of the algorithm for constructing structural models.  Results of the proposed algorithm's verification are provided, as well as their comparison with other character recognition algorithms. Algorithms that can operate under a limited number of reference images were used for the comparison.

Keywords:
character recognition, structural components, structural models, computer vision, skeletonization, binarization.

Citation:
Khaustov PA. Algorithms for handwritten character recognition based on constructing structural models. Computer Optics 2017; 41(1): 67-78. DOI: 10.18287/2412-6179-2017-41-1-67-78.

References:

  1. Mori Sh, Suen ChY, Yamamoto K. Historical review of OCR research and development. Proc IEEE 1992; 80(7): 1029-1058. DOI: 10.1109/5.156468
  2. Helinski M, Kmieciak M, Parkola T. Report on the comparison of Tesseract and ABBYY FineReader OCR engines. Technical report. Poznañ, Poland: Poznañ Supercomputing and Networking Center; 2012.
  3. Spitsyn VG, Bolotova YuA, Phan NH, Bui TTT. Using a Haar wavelet transform, principal component analysis and neural networks for OCR in the presence of impulse noise. Computer Optics 2016; 40(2): 249-257. DOI: 10.18287/2412-6179-2016-40-2-249-257.
  4. Breuel TM, Ul-Hasan A, Azawi MAl, Shafait F. High-Performance OCR for Printed English and Fraktur using LSTM Networks. Proc 12th International Conference on Document Analysis and Recognition 2013: 683-687. DOI: 10.1109/ICDAR.2013.140.
  5. Jaderberg M, Simonyan K, Vedaldi A, Zisserman A. Reading Text in the Wild with Convolutional Neural Networks. International Journal of Computer Vision 2016; 116(1): 1-20. DOI: 10.1007/s11263-015-0823-z.
  6. Wang T, Wu DJ, Coates A, Ng AY. End-to-End Text Recognition with Convolutional Neural Networks. Proc ICRP 21 2012: 3304-3308.
  7. Lotfi M, Solimani A, Dargazany A, Afzal H, Bandarabadi M. Combining wavelet transforms and neural networks for image classification. SSST 2009: 44-48. DOI: 10.1109/SSST.2009.4806819.
  8. Wang PSP, Gupta A. An improved structural approach for auto-mated recognition of handprinted characters. Int J Patt Recog Artif Intell 1991; 05(01n02): 97-121. DOI: 10.1142/S0218001491000089.
  9. Otsu NA. Threshold Selection Method From Gray-level Histograms. IEEE Trans Sys, Man, Cybern 1979; SMC-9(1): 62-66.
  10. Widiarti AR. Comparing Hilditch, Rosenfeld, Zhang-Suen, and Nagendraprasad-Wang-Gupta Thinning. International Journal of Computer, Electrical, Automation, Control and Information Engineering 2011; 5(6): 20-24.
  11. Zhang TY, Suen CY. A Fast Parallel Algorithm for Thinning Digital Patterns. Communications of the ACM 1984; 27(3): 236-239. DOI: 10.1145/357994.358023.
  12. Wu R-Y, Tsai W-H. A new one-pass parallel thinning algorithm for binary images. Pattern Recognition Letters 1992; 13(10): 715-723. DOI: 10.1016/0167-8655(92)90101-5.
  13. Lee CY. An Algorithm for Path Connections and Its Applications. IRE Transactions on Electronic Computers 1961; EC-10(3): 346-365. DOI: 10.1109/TEC.1961.5219222.
  14. Gradshtein IS, Ryzhik IM. Tables of integrals, series and products (Corrected and enlarged edition). London: Academic Press, Inc.; 1980. ISBN: 978-0-12-294760-5.
  15. Christofides N. Graph Theory. An Algorithmic Approach. Orlando, FL, USA: Academic Press, Inc.; 1975. ISBN: 978-0121743505.
  16. Khaustov PA, Spitsyn VG, Maksimova EI. Genetic algorithm of set of lines searching for optical character recognition based on the method of intersections [In Russian]. Modern problems of science and education 2014; 6.
  17. Vapnik VN, Cortes C. Support Vector Networks. Machine Learning 1995; 20(3): 273-297. DOI: 10.1023/A:1022627411411.
  18. Khaustov PA, Grigoryev DS, Spitsyn VG. The development of optical character recognition approach on the basis of joint application of probabilistic neural network and wavelet transform [In Russian]. Bulletin of the Tomsk Polytechnic University 2013; 323(5): 101-105.
  19. LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient based learning applied to document recognition. Proceedings of the IEEE 1998; 86(11): 2278-2324. DOI: 10.1109/5.726791.
© 2009, IPSI RAS
Institution of Russian Academy of Sciences, Image Processing Systems Institute of RAS, Russia, 443001, Samara, Molodogvardeyskaya Street 151; E-mail: journal@computeroptics.ru; Phones: +7 (846) 332-56-22, Fax: +7 (846) 332-56-20