Optical Memory and Neural Networks

, Volume 26, Issue 2, pp 117–128 | Cite as

Farsi/Arabic handwritten digit recognition using quantum neural networks and bag of visual words method

  • Gholam Ali Montazer
  • Mohammad Ali Soltanshahi
  • Davar Giveki
Article
  • 50 Downloads

Abstract

Handwritten digit recognition has long been a challenging problem in the field of optical character recognition and of great importance in industry. This paper develops a new approach for handwritten digit recognition that uses a small number of patterns for training phase. To improve performance of isolated Farsi/Arabic handwritten digit recognition, we use Bag of Visual Words (BoVW) technique to construct images feature vectors. Each visual word is described by Scale Invariant Feature Transform (SIFT) method. For learning feature vectors, Quantum Neural Networks (QNN) classifier is used. Experimental results on a very popular Farsi/Arabic handwritten digit dataset (HODA dataset) show that proposed method can achieve the highest recognition rate compared to other state of the arts methods.

Keywords

farsi/arabic handwritten digit recognition SIFT BoVW QNN 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Salimi, H. and Giveki, D., Farsi/Arabic handwritten digit recognition based on ensemble of SVD classifiers and reliable multi-phase PSO combination rule, Int. J. Document Anal. Recognit. (IJDAR), 2012.Google Scholar
  2. 2.
    Pan, W.M., Bui, T.D., and Suen, C.Y.: Isolated handwritten Farsi numerals recognition using sparse and overcomplete representations, 10th International Conference on Document Analysis and Recognition, 2009, pp. 586–590.Google Scholar
  3. 3.
    Sadri, J., Suen, C.Y., and Bui, T.D., Application of support vector machines for recognition of handwritten Arabic/Persian digits, Proceedings of the 2nd Conference on Machine Vision and Image Processing and Applications, 2003, vol. 1, pp. 300–307.Google Scholar
  4. 4.
    Soltanzadeh, H. and Rahmati, M., Recognition of persian handwritten digits using image profiles of multiple orientations, Patern Recognit. Lett., 2004, vol. 25, no. 14, pp. 1569–1576.CrossRefGoogle Scholar
  5. 5.
    Mowlaei, A. and Faez, K., Recognition of isolated handwritten Persian/Arabic characters and numerals using support vector machines, Proceedings IEEE 13th Workshop on Neural Networks for Signal Processing, 2003, pp. 547–554.Google Scholar
  6. 6.
    Ziaratbanv, M., Faez, K., and Faradji, F., Language-based feature extraction using template-matching in Farsi/Arabic handwritten numeral recognition, Proceedings Ninth International Conference on Document Analysis and Recognition, 2007, vol. 1, pp. 297–301.Google Scholar
  7. 7.
    LeCun, Y., Bottou, L., Bengio, Y., and Haffner, P., Gradient based learning applied to document recognition, Proc. IEEE, 1998, vol. 86, no. 11, pp. 2278–2324.CrossRefGoogle Scholar
  8. 8.
    Broumandnia, A., Shanbehzadeh, J., and RezakhahVarnoosfaderani, M., Persian/Arabic handwritten word recognition using M-band packet wavelet transform, Image Vis. Comput. Elsevier, 2008, vol. 26, pp. 829–842.CrossRefGoogle Scholar
  9. 9.
    Chen, C.H. and Wang, P.S.P., Handbook of Pattern Recognition and Computer Vision, 3rd ed., Singapore: World Scientific, 2005.Google Scholar
  10. 10.
    Hanmandlu, M., Grover, J., Madasu, V.K., and Vasikarla, S., Input fuzzy modeling for the recognition of handwritten Hindi numeral, International Conference on Informational Technology, 2007, vol. 2, pp. 208–213.Google Scholar
  11. 11.
    Jolliffe, I.T., Principal Component Analysis, New York: Springer, 1986.Google Scholar
  12. 12.
    Liu, C.L. and Suen, C.Y., A new benchmark on the recognition of handwritten Bangla and Farsi numeral characters, Patern Recognit., 2008, vol. 42, pp. 3287–3295.CrossRefMATHGoogle Scholar
  13. 13.
    Rajashekararadhya, S.V., Ranjan, P.V., and ManjunathAradhya, V.N., Isolated handwritten Kannada and Tamil numeral recognition: a novel approach, First International Conference on Emerging Trends in Engineering and Technology ICETET, 2008, no. 8, pp. 1192–1195.Google Scholar
  14. 14.
    Wshah, S., Shi, Z., and Govindaraju, V., Segmentation of Arabic handwriting based on both contour and skeleton segmentation, 10th International Conference on Document Analysis and Recognition, 2009.Google Scholar
  15. 15.
    Yang, J., Zhang, D., Frangi, A.F., and Yang, J.Y., Two-dimensional PCA: A new approach to appearance-based face representation and recognition, IEEE Trans. Pattern Anal. Machine Intelligence, 2004, pp. 131–137.Google Scholar
  16. 16.
    Lowe, D.G., Distinctive image features from scale-invariant keypoints, Int. J. Comput. Vision, 2004, vol. 60, no. 2, pp. 91–110.CrossRefGoogle Scholar
  17. 17.
    Lazebnik, S., Schmid, C., and Ponce, J., Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories, IEEE ComputeSociety Conference on Computer Vision and Pattern Recognition, 2006, vol. 2, pp. 2169–2178.Google Scholar
  18. 18.
    Avila, S., Thome, N., Cord, M., Valle, E., and de Araújo, A., Bossa: Extended bow formalism for image classification, International Conference on Image Processing, 2011, pp. 2966–2969.Google Scholar
  19. 19.
    Zhu, D. and Wu, R.A., Multi-layer quantum neural networks recognition system for handwritten digital recognition pattern recognition, IEEE International Conference on Natural Computation, 2007, vol. 1, pp. 718–722.Google Scholar
  20. 20.
    Khosravi, H. and Kabir, E., Introducing a very large dataset of handwritten Farsi digit and a study on their varieties, Patern Recognit. Lett., 2007, vol. 28, pp. 1133–1141.CrossRefGoogle Scholar
  21. 21.
    Csurka, G., Bray, C., Dance, C., and Fan, L.,Visual categorization with bags of keypoints, Workshop on Statistical Learning in Computer Vision, ECCV, Prague, Czech Republic, 2004, pp. 1–22.Google Scholar
  22. 22.
    Opelt, A., Pinz, A., and Zisserman, A., A boundary-fragment-model for Scene detection, European Conference on Computer Vision, Graz, Austria, 2006, vol. 2, pp. 575–588.Google Scholar
  23. 23.
    Jing Yu, Zengchang Qin, Tao Wan, and Xi Zhang, Feature integration analysis of bag-of-features model for image retrieval, Neurocomputing, 2013, vol. 120, pp. 355–364.CrossRefGoogle Scholar
  24. 24.
    Penatti, Otávio A.B., Silva, Fernanda B., Eduardo Valle, Valerie Gouet-Brunet, and Ricardo da S. Torres, Visual word spatial arrangement for image retrieval and classification, Patern Recognit., 2014, vol. 47, pp. 705–720.CrossRefGoogle Scholar
  25. 25.
    Shiliang Zhang, Qi Tian, Gang Hua, Qingming Huang, and Wen Gao, ScenePatchNet: Towards scalable and semantic image annotation and retrieval, Comput. Vision Image Understanding, 2014, vol. 118, pp. 16–29.CrossRefGoogle Scholar
  26. 26.
    Zhang, H., Berg, A., Maire, M., and Malik, J., SVM-KNN: Discriminative nearest neighbor classification for visual category recognition, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2006, vol. 2, pp. 2126–2136.Google Scholar
  27. 27.
    Leung, T. and Malik, J., Representing and recognizing the visual appearance of materials using three-dimensional textons, Int. J. Comput. Vision, 2001, vol. 43, no. 1, pp. 29–44.CrossRefMATHGoogle Scholar
  28. 28.
    Sivic, J. and Zisserman, A., Video Google: A text retrieval approach to Scene matching in videos, International Conference on Computer Vision, 2003, vol. 2, pp. 1470–1477.Google Scholar
  29. 29.
    Fei-Fei, L. and Perona, P., A bayesian hierarchical model for learning natural scene categories, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005, vol. 2, pp. 524–531.Google Scholar
  30. 30.
    Gopathy, P., Nicolaos, B., and Karayiannis, N.B., Quantum Neural networks: Inherently fuzzy feedforward neural networks, J. IEEE Trans. Neural Networks, 1997, vol. 8, no. 3, pp. 679–693.CrossRefMATHGoogle Scholar
  31. 31.
    http://farsiocr.ir/farsi-digit-dataset.Google Scholar
  32. 32.
    Antoine, J.P., Vandergheynst, P., Bouyoucef, K., and Murenzi, R., Target detection and recognition using twodimensional isotropic and anisotropic wavelets, Aut. Object Recognit. V: SPIE Proc., 1995, vol. 2485, pp. 20–31.CrossRefGoogle Scholar
  33. 33.
    Antoine, J.P. and Murenzi, R., Two dimensional directional wavelets and the scale-angle representation, Signal Process., 1996, vol. 53, pp. 259–281.CrossRefMATHGoogle Scholar
  34. 34.
    Kaplan, L. and Murenzi, R., Pose estimation of SAR imagery using the two dimensional continuous wavelet transform, Patern Recognit. Lett., 2003, vol. 24, pp. 2269–2280.CrossRefMATHGoogle Scholar
  35. 35.
    Romero, D.J., Seijas, L.M., and Ruedin, A.M., Directional continuous wavelet transform applied to handwritten numerals recognition using neural networks, JCS, 2007, vol. 7, no. 1, pp. 66–71.Google Scholar
  36. 36.
    Jain, A.K., Prabhakar, S., Hong, L., and Pankanti, S., FingerCode: A filterbank for fingerprint representation and matching. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1999, vol. 2, pp.Google Scholar
  37. 37.
    Shirali-Shahreza, H., Faez, K., and Khotanzad, A., Recognition of hand-written persian/arabic numerals by shadow coding and an edited probabilistic neural network, Proceedings of International Conference on Image Processing, 1995, vol. 3, pp. 436–439.Google Scholar
  38. 38.
    Dehghan, M. and Faez, K., Farsi handwritten character recognition with moment invariants, Proceedings of 13th International Conference on Digital Signal Processing, 1997. 2, pp. 507–510.CrossRefGoogle Scholar
  39. 39.
    Harifi, A. and Aghagolzadeh, A., A new pattern for handwritten persian/arabic digit recognition, J. Inform. Technol., 2004, vol. 3, pp. 249–252.Google Scholar
  40. 40.
    Mir Mohammad Hosseini, H. and Bouzerdoum, A., A combined method for Persian and Arabic handwritten digit recognition, Australian New Zealand Conference on Intelligent Information System, 1996, pp. 80–83.Google Scholar
  41. 41.
    Mowlaei, A., Faez, K., and Haghighat, A., Feature extraction with wavelet transform for recognition of isolated handwritten farsi/arabic characters and numerals, Digital Signal Process., 2002, vol. 2, pp. 923–926.Google Scholar
  42. 42.
    Mozaffari, S., Faez, K., and Ziaratban, M., Structural decomposition and statistical description of Farsi/Arabic handwritten numeric characters, Proceedings of the 8th Int. Conference on Document Analysis and Recognition, 2005, vol. 1, pp. 237–241.Google Scholar
  43. 43.
    Alaei, A., Pal, U., and Nagabhushan, P., Using modified contour features and SVM based classifier for the recognition of Persian/Arabic handwritten numerals, Seventh International Conference on Advances in Pattern Recognition, 2009.Google Scholar
  44. 44.
    Reza Ebrahimpour, Alireza Esmkhani, and Soheil Faridi, Farsi handwritten digit recognition based on mixture of RBF experts, IEICE Electron. Express., 2010, vol. 7, no. 14, pp. 1014–1019.CrossRefGoogle Scholar
  45. 45.
    Abdi, M.J. and Salimi, H., Farsi handwriting recognition with mixture of RBF experts based on particle swarm optimization, Int. J. Inf. Sci. Comput. Math., 2010, vol. 2, pp. 129–136.Google Scholar

Copyright information

© Allerton Press, Inc. 2017

Authors and Affiliations

  • Gholam Ali Montazer
    • 1
  • Mohammad Ali Soltanshahi
    • 1
  • Davar Giveki
    • 1
  1. 1.School of Engineering, Department of Information Technology EngineeringTarbiat Modares UniversityTehranIran

Personalised recommendations