IJBTT

Signature Matching Using Associative Memory with Reusing of Pruned Nodes

	International Journal of Engineering Trends and Technology (IJETT)
	© 2017 by IJETT Journal
	Volume-43 Number-1
	Year of Publication : 2017
	Authors : K. Nagi Reddy, Dr.B Ravi Prasad, Dr.K.Suvarchala
	DOI :  10.14445/22315381/IJETT-V43P203

Citation 

K. Nagi Reddy, Dr.B Ravi Prasad, Dr.K.Suvarchala "Signature Matching Using Associative Memory with Reusing of Pruned Nodes", International Journal of Engineering Trends and Technology (IJETT), V43(1),10-16 January 2017. ISSN:2231-5381. www.ijettjournal.org. published by seventh sense research group

Abstract
Signature matching has been a topic of interest for quite some time. The need for efficient and robust algorithms and systems for recognition is being experienced in India especially in the post and telegraph department, banking sector and police department. In this paper signature image database retrieval has been investigated with special consideration. In unformatted databases one of the important features is that the user tends to retrieve information based on approximate queries, which are quite common in practice and sometimes unintentional. Work has been done on signature matching earlier using conventional and hybrid methods which may not be very efficient for practical systems. The present work is a new direction in signature matching using artificial neural networks and an implementation of a comprehensive software, based on signature matching in practice. Our procedure involves capturing the signature image, preprocessing, indexing each signature image through wavelets, thresholding and retrieving the stored signature for the given query signature pattern using associative memory concept of Dynamical Neural Network (DNN) with reuse. It is proved that the performance of the dynamical neural network with reuse using the learning strategy for signature matching is very efficient.

 References

[1] Rao, M.S., Arun K Pujari and sreenivasan. B. A New Neural Network architecture with associate memory, Pruning and order sensitive learning. International Journal of neural Systems 9, 4, 351-370, 1999.
[2] Falutsos, C. Access methods for text. ACM Computing Surveys, 17, 1, 49-74, 1985.
[3] Hall, P.A.V. Dowling. G.R. Approximate string matching. ACM Computing Surveys, 12, 4, 381-402, 1980.
[4] Rao, M.S., Arun K Pujari and sreenivasan. B. A New Neural Network architecture for efficient close proximity match of large databases. Proceedings of the Eighth International Workshop on DEXA, France, IEEE Computer Society Press, 444-449, 1997.
[5] Knuth, D.E., Morris, J.H., Pratt, V.R. Fast pattern Matching strings, SIAM Journal of Computing, 6, 2, 323-350, 1977.
[6] Hollar, L.A., Smith, K.F., Chow, W.H., Emrath, P.A., Haskin, R.L. Architecture and operation of large, full-text information retrieval system. Advanced Database Machine Architecture, D.K. Hsiao, Ed. Prentice Hall, Englewood Cliffs, New Jersey, 256-299, 1983.
[7] Lesk, M. Some applications of inverted indexes on the UNIX system. UNIX Programmers manual, Bell Laboratories, Marray Hill, New Jersey, 1978.
[8] Salton, G., Fox, E.A. Wu, H. Extended Boolean information retrieval Communication. ACM, 26, 11, 1022-1036, November, 1983.
[9] Tsichritzis, D., Christodoulakis, S. Message files, ACM Transactions on Office Information Systems, 1, 1, 88-98, 1983.
[10] Larson, P.A. A method for speeding up text retrieval. Proceedings of the ACM SIGMOD Conference, ACM, New York, 1983.
[11] Sack-Davis, R., Kent, A., K. Ramamohanarao. Multikey access methods based on superimposed coding technique. ACM Transaction on Database System, 12, 4, 655-696, 1987.
[12] M.J. Smith and T.P. Barnwell. Anew filter Bank theory for itme-frequency representation. IEEE Transaction on Acoustics, Speech and Signal Processing, 35, 314-327, March, 1987.
[13] Lippman, R. An introduction to computing with neural nets, IEEE ASSP magazine 4-22, 1987.
[14] McEliece, R.J., Posner, E.C., Rodemich, E.R. and Venkatesh, S.S. The capacity of the Hopfield associative memory, IEEE Trans on Inform Theory 33, 641, 1987.
[15] M Swamy Das, D Sandhya Rani, C R K Reddy, A Govardhan""Script Identification from Multilingual Telugu, Hindi and English Text documents", International Journal of wisdom Based Computing, Vol. 1(3), December 2011.
[16]B.M Sagar, Dr.G.Shoba, Dr. P.Ramakanth Kumar," Character Segmentation algorithms for kannada optical character Recognition", Proceedings of the 2008 International Conference on Wavelet Analysis and Pattern Recognition.

Keywords
—associative memory, dynamical neural network, spurious states, string descriptor, thresholding, POSC