World Academy of Science, Engineering and Technology
Published April 22, 2009 | Version 14126
Journal article Open

Bi-lingual Handwritten Character and Numeral Recognition using Multi-Dimensional Recurrent Neural Networks (MDRNN)

Creators

Description

The key to the continued success of ANN depends, considerably, on the use of hybrid structures implemented on cooperative frame-works. Hybrid architectures provide the ability to the ANN to validate heterogeneous learning paradigms. This work describes the implementation of a set of Distributed and Hybrid ANN models for Character Recognition applied to Anglo-Assamese scripts. The objective is to describe the effectiveness of Hybrid ANN setups as innovative means of neural learning for an application like multilingual handwritten character and numeral recognition.

Files

14126.pdf

Files (269.2 kB)

Name Size Download all
md5:2fc2db9ee4f4221278187011b675db69
269.2 kB Preview Download

Additional details

References

  • R. Rojas, Neural Networks A Systematic Introduction, Springer, Berlin, 1996.
  • S. Haykin, Neural Networks- A Comprehensive Foundation, 2nd Ed., Pearson Education, New Delhi, 2003.
  • J. L. McClelland and D. E. Rumelhart, "Distributed Memory and the Representation of General and Specific Information," Journal of Experimental Psychology: General, 114, pp. 159-188 1985.
  • D. E. Rummelhart, G. E. Hinton and R. J. Williams, "Learning Representations by Back-Propagation Errors," Nature, 323, pp. 533-536 1986.
  • T. Alvager, D. P. Beach and D. Herrmann, "A Hardware Implementation of Artificial Neural Networks," Advanced Neural Computing Research Center Annual Report, Aspen Technology Indiana State University, Terre Haute, IN, USA, 2001.
  • M. Misra, "Implementation of Neural Networks on Paralel Architectures", PhD Thesis Presented to the Faculty of the Graduate School University of Southern California, December, 1992.
  • U. A. Muler, A. Gunzinger and W. Guggenbuh, "Fast Neural Net Simulation with a DSP Processor Array", Electronics Laboratory, Swis Federal Institute of Technology, February, 1993.
  • N. B. Serebdzija, "Simulating Artificial Neural Networks on Parallel Architectures", Computer, Vol. 29, No. 3, pp. 56-63, 1996.
  • T. Schoenauer, A. Jahnke, U. Roth and H. Klar, "Digital Neurohardware: Principles and Perspectives", Neuronal Networks in Applications - NN-98 - Magdeburg, pp. 101-106, 1998 [10] N. Sundararajan and P. Saratchandran , "Parallel Architectures for Artificial Neural Networks ", Journal of the Institute of Electrical and Electronics Engineers Inc., 1998. [11] T. Heirs, "A High Performance Multiprocessor DSP System", Masters Thesis, Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, May, 2001 [12] K. K. Sarma, P. K. Bora and C. Mahanta, "Innovative Feature Set for Multi Layered Perceptron (MLP) Based Assamese Character Recognition", Proceedings of 2nd Indian International Conference on Artificial Intelligence (IICAI-2005), pp. 473- 491, 2005. [13] K. K. Sarma, "Novel Feature Set for Neural Character Recognition " , Proc. of the 5th International Symposium on Robotics and Automation, San Miguel Regla Hidalgo, Mexico , pp. 409-414, August, 2006. [14] K. K. Sarma, "MLP-based Assamese Character and Numeral Recognition using an Innovative Hybrid Feature Set", Proc. Of the Proceedings of 3rd Indian International Conference on Artificial Intelligence (IICAI- 2007), Pune, India , pp. 585 -600, December, 2007. [15] K. K. Sarma, "Modified Hybrid Feature Set for Assamese Character and Anglo-Assamese Hand Written Numeral Recognition", International Journal of Imaging, Volume 1, pp. 13 -28, Autumn 2008. [16] K. Bhattacharjya and K. K. Sarma, "ANN-based Innovative Segmentation Method for Handwritten text in Assamese", IJCSI International Journal of Computer Science Issues, Vol. V, No. IJCSI-2009-10-20, October, 2009.