Abstract

It is herein proposed a handwritten digit recognition system which biologically inspired of the large-scale structure of the mammalian neocortex. Hierarchical Temporal Memory (HTM) is a memory-prediction network model that takes advantage of the Bayesian belief propagation and revision techniques. In this article a study has been conducted to train a HTM network to recognize handwritten digits and letters taken from the well-known Hoda dataset for Farsi handwritten digit. Results presented in this paper show good performance and generalization capacity of the proposed network for a real-world big dataset.

References

• V. Ghods and M. K. Sohrabi, "Online Farsi digit recognition using their upper half structure," in Sixth International Conference on Graphic and Image Processing (ICGIP 2014), 2015, pp. 94430B-94430B-6.
• Ping Zhang, Reliable recognition of handwritten digits using a cascade ensemble classifier system and hybrid features, Ph.D. thesis, Concordia University, Montreal, P.Q., Canada, 2006.
• Fabien Lauer, Ching Y. Suen, and Gérard Bloch, “A trainable feature extractor for handwritten digit recognition,” Pattern Recognition, vol. 40, no. 6, pp. 1816–1824, 2007.
• Patrice Y. Simard, Dave Steinkraus, and John C. Platt, “Best practices for convolutional neural networks applied to visual document analysis,” International Conference on Document Analysis and Recognition, vol. 2, pp. 958–963, 2003.
• E.M. Kussul, T.N. Baidyk, D.C. Wunsch, O. Makeyev, and A. Martin, “Permutation coding technique for image recognition systems,” IEEE Transactions on Neural Networks, vol. 17, no. 6, pp. 1566–1579, 2006.
• Price, Ryan William. Hierarchical Temporal Memory Cortical Learning Algorithm for Pattern Recognition on Multi-core Architectures. Diss. Portland State University, 2011.
• Hawkins, J., Blakeslee, S. (2004). On intelligence. Henry Holt and Company, New York.
• George, D., Hawkins, J. (2009). Towards a mathematical theory of cortical micro-circuits. PLoS Computational Biology 5(10). DOI 10.1371/journal.pcbi.1000532.
• George, D., Jaros, B. 2007. The htm learning algorithms. Whitepaper, Numenta Inc.
• Numenta (2007). Zeta1 algorithms reference. Document version 1.0.
• Chauchard, F., et al. "Application of LS-SVM to non-linear phenomena in NIR spectroscopy: development of a robust and portable sensor for acidity prediction in grapes." Chemometrics and Intelligent Laboratory Systems 71.2 (2004): 141-150.
• George, D., Hawkins, J.: A hierarchical bayesian model of invariant pattern recognition in the visual cortex. In: Proceedings of 2005 IEEE International Joint Conference on Neural Networks, IJCNN 2005, July 4-August, vol. 3, pp. 1812–1817 (2005)
• Numenta (2009). Numenta node algorithms guide, NuPIC 1.7.
• Kostavelis, I., Gasteratos, A., 2011. Laboratory of Robotics and Automation.http://utopia.duth.gr/~gkostave/downloads/operation_of_nodes_in_the_first_level.rar
• Khosravi, H., Kabir, E.: Introducing a very large dataset of handwritten Farsi digits and a study on their varieties. Pattern Recognit. Lett. 28(10), 1133–1141 (2007).
• Chang, C.C., Lin, C.J., 2011. LIBSVM: A library for support vector machines. ACM Trans. Intell. Syst. Technol. 2, 27:1–27:27, Software available at http:// www.csie.ntu.edu.tw/~cjlin/libsvm.
• M. Hanmandlu, O.V. Ramana Murthy, Fuzzy model based recognition of handwritten numerals, the journal of pattern recognition society, pp. 1840 – 1854, 2006.
• N. Otsu, “A Threshold Selection Method from Gray-Level Histograms,” Systems, Man and Cybernetics, IEEE Transactions on, vol. 9, no. 1, pp. 62-66, 1979.
• S. mozaffari, K. faez, F. Faradji et al., "A comprehensive isolated Farsi/Arabic character database for handwritten OCR research." pp. 385-389.
• M. Ziaratban, K. Faez and F. Faradji “Language-Based Feature Extraction using Template-Matching in Farsi/Arabic Handwritten Numeral Recognition”, Proceedings of 9th International Conference on Document Analysis and Recognition, vol.1, pp. 297-301, 2007.
• M. H. Shirali-Shahreza, K. Faze and A. Khotanzad, “Recognition of Hand-written Persian/Arabic Numerals by Shadow Coding and an Edited Probabilistic Neural Network“, Proceedings of International Conference on Image Processing, vol. 3, pp. 436-439, 1992.
• K. Fouladi, B. N. Araabi, and E. Kabir, "A fast and accurate contour-based method for writer-dependent offline handwritten Farsi/Arabic subwords recognition," International Journal on Document Analysis and Recognition (IJDAR), vol. 17, pp. 181-203, 2014.
• A. Mowlaei and K.Faez, “Recognition Of Isolated Handwritten Persian /Arabic Characters and Numerals Using Support Vector Machines”, Proceedings of XIII Workshop on Neural Networks for Signal Processing, pp. 547-554, 2003.
• R. Ebrahimpur, A. Esmkhani, and F. Faradji, “Farsi handwritten digit recognition based on mixture of RBF experts,” IEICE Electron. Express, vol. 7, no. 14, pp. 1014-1019, 2010.
• M. M. Javidi, and f. Sharifizadeh, “A Modified Decision Templates Method for Persian Handwritten Digit Recognition,” Journal of American Science, vol. 8, no. 1, pp. 504-512, 2012.
• S. Mozaffari, K. Faez & H. Rashidy Kanan, “Recognition of Isolated Handwritten Farsi/Arabic Alphanumeric Using Fractal Codes”, Image Analysis and Interpretation, 6thSouthwest Symposium, pp. 104-108, 2004.
• H. Soltanzadeh and M. Rahmati, “Recognition of Persian handwritten digits using image profiles of multiple orientations”, Pattern Recognition Letters 25, pp. 1569–1576, 2004.
• A. Harifi and A. Aghagolzadeh,” A New Pattern for Handwritten Persian/Arabic Digit Recognition”, Journal of Information Technology vol. 3, pp. 249-252, 2004.
• M. R. Keyvanpour, R. Azmi, Z. S. M. Tabatabai, and Z. Abdolhosseini, "Handwriting Persian character recognition using optimized structural elements," Global Journal of Information Technology, vol. 4, 2015.
• S. Mozaffari, K. Faez and M. Ziaratban, “Structural Decomposition and Statistical Description of Farsi/Arabic Handwritten Numeric Characters”, Proceedings of the 8th Intl. Conference on Document Analysis and Recognition, vol. 1, pp. 237- 241, 2005.
• A. Mowlaei, K. Faez ,A. Highlight, ”Feature Extraction with Wavelet Transform for Recognition of Isolated Handwritten Farsi/Arabic Characters and Numerals”, Digital Signal Processing vol. 2, pp. 923- 926, 2002.
• J. Sadri, C. Y. Suen and T. D. Bui, “Application of Support Vector Machines for Recognition of Handwritten Arabic/Persian Digits”, Proceedings of the 2nd Conference on Machine Vision and Image Processing & Applications, vol. 1, pp. 300-307, 2003.
• R. Ebrahimpur, M. R. Moradian, A. Esmkhani et al., “Recognition of Persian handwritten digits using Characterization Loci and Mixture of Experts,” International Journal of Digital Content Technology and its Applications, vol. 3, 2009
• Rashnodi, Omid, Hedieh Sajedi, and Mohammad Saniee Abadeh. "Using Box Approach in Persian Handwritten Digits Recognition." International Journal of Computer Applications 32.3 (2011)..
• Rashnodi, Omid, Hedieh Sajedi, and Mohammad Saniee Abadeh. "Persian Handwritten Digit Recognition using Support Vector Machines." International Journal of Computer Applications 29.12 (2011).
• A. Alaei, P. Nagabhushan, and U. Pal, "A New Two-Stage Scheme for the Recognition of Persian Handwritten Characters." pp. 130-135.
• S. Mozaffari, K. Faez, and H. R. Kanan, "Recognition of isolated handwritten Farsi/Arabic alphanumeric using fractal codes." pp. 104-108.
• M. Dehghan, and K. Faez, "Farsi handwritten character recognition with moment invariants." pp. 507-510 vol.2.
• J. Shanbezadeh, H. Pezashki, and A. Sarrafzadeh, "Features Extraction from Farsi Hand Written Letters." pp. 35-40.
• A. Mowlaei, and K. Faez, "Recognition of isolated handwritten Persian/Arabic characters and numerals using support vector machines." pp. 547-554.
• M. R. Keyvanpour, R. Azmi, Z. S. M. Tabatabai, and Z. Abdolhosseini, "Handwriting Persian character recognition using optimized structural elements," Global Journal of Information Technology, vol. 4, 2015.
• K. Fouladi, B. N. Araabi, and E. Kabir, "A fast and accurate contour-based method for writer-dependent offline handwritten Farsi/Arabic subwords
• recognition," International Journal on Document Analysis and Recognition (IJDAR), vol. 17, pp. 181-203, 2014