We apologize for a recent technical issue with our email system, which temporarily affected account activations. Accounts have now been activated. Authors may proceed with paper submissions. PhDFocusTM
CFP last date
20 December 2024
Reseach Article

A Comparative Study on the Development of Binary Object Extraction System using Different Self Organizing Neural Network

by Harshshikha Nandan, Manisha Jindal, Arsh, Debanjan Konar
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 117 - Number 22
Year of Publication: 2015
Authors: Harshshikha Nandan, Manisha Jindal, Arsh, Debanjan Konar
10.5120/20687-3554

Harshshikha Nandan, Manisha Jindal, Arsh, Debanjan Konar . A Comparative Study on the Development of Binary Object Extraction System using Different Self Organizing Neural Network. International Journal of Computer Applications. 117, 22 ( May 2015), 24-29. DOI=10.5120/20687-3554

@article{ 10.5120/20687-3554,
author = { Harshshikha Nandan, Manisha Jindal, Arsh, Debanjan Konar },
title = { A Comparative Study on the Development of Binary Object Extraction System using Different Self Organizing Neural Network },
journal = { International Journal of Computer Applications },
issue_date = { May 2015 },
volume = { 117 },
number = { 22 },
month = { May },
year = { 2015 },
issn = { 0975-8887 },
pages = { 24-29 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume117/number22/20687-3554/ },
doi = { 10.5120/20687-3554 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T23:00:06.924929+05:30
%A Harshshikha Nandan
%A Manisha Jindal
%A Arsh
%A Debanjan Konar
%T A Comparative Study on the Development of Binary Object Extraction System using Different Self Organizing Neural Network
%J International Journal of Computer Applications
%@ 0975-8887
%V 117
%N 22
%P 24-29
%D 2015
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Accurately Extraction of a binary object from a noisy perspective has been a daunting task in the field of pattern recognition. Several techniques have been tried to optimally solve the problem of denoising of object over the decades. In this paper, different binary object extraction methods are reviewed which are basically guided by different Self-Organizing Neural Networks (SONN) architectures as Bi-Directional Self Organizing Neural Network (BDSONN), multi-Layer Self Organizing neural Network (MLSONN) and quantum version of MLSONN (QMLSONN). The result shows that QMLSONN outperforms over other network architectures in terms of time and also it restores shape of the object with great accuracy.

References
  1. Forrest, B. M. et al 1988 Neural network models. Parallel Computation 8:71–83
  2. Lippmann, R. P. 1987 An introduction to computing with neural nets. IEEE ASSP Magazine, 3–22.
  3. Hay, K. S. 1994 neural networks: a comprehensive foundation. Macmillan College, New York.
  4. Hertz, J. , Krogh, A. , Palmer, R. G. 1991 Introduction to the theory of neural computation.
  5. Antonucci, M. , Tirozzi, B. , Yarunin N. D. et al. 1994 "Numerical simulation of neural networks with translation and rotation invariant pattern recognition," International Journal of Modern Physics B, vol. 8, no. 11-12, pp. 1529-1541
  6. Pao, Y. H. , 1989 Adaptive pattern recognition and neural networks. Addison-Wesley, New York]
  7. Wesley, A. , Ekstrom, M. P. 1984 Digital image processing techniques. Academic, New York G.
  8. Bilbro, G. L. , White, M. , Synder, W. 1988 Image segmentation with neuro computers. In: Eckmiller R, Malsburg CVD (eds) Neural computers. Springer, New York.
  9. Kim, T. , Devarajan, B. and Manry, M. "Road extraction from aerial images using neural networks," Proceedings of ASPRS Annual Convention, vol. 3, pp. 146-154
  10. Carpenter, A. and Ross, W. D. 1995 "ART-EMAP: A neural network architecture for object recognition by evidence accumulation," IEEE Transactions on Neural Networks, vol. 6, no. 4, pp. 805-818
  11. Abdallah, M. A. , Samu, T. I. , Grisson, W. A. 1995 Automatic target identification using neural networks. SPIE Proc Intell Robots Comput Vis XIV 2588:556–565V]
  12. Tang, H. W. , Srinivasan, V. , Ong, S. H. 1996 Invariant object recognition using a neural template classifier. Image VisComput14(7):473–483
  13. Tou, J. T. and Gonzalez, R. C. Pattern Recognition Principles, Reading, MA: Addison Wesley, 1974
  14. Chua, L. O. , Yang, L. 1988 Cellular neural network: theory. IEEE Trans Circuits Syst 35:1257–1272 ]
  15. Kosko, B. 1988 Bidirectional associative memories. IEEE Trans Syst
  16. Duda, R. O. , Hart, P. E. 1973 Pattern classification and scene analysis. Wiley, New York
  17. Kosko, B. 1992 Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence. Prentice-Hall, Englewood Cliffs
  18. Zamparel, M. 1997 Genetically trained cellular neural networks. Neural Network 10(6):1143–1151
  19. Bhattacharyya, S. , Dutta, P. , Maulik, U. and Nandi, P. K. - Intelligent Technology Volume 1 Number 4A Self Supervised Bi-directional Neural Network (BDSONN) Architecture for Object Extraction Guided by Beta Activation Function and Adaptive Fuzzy Context Sensitive Thresholding.
  20. Bhattacharya, S. , Dutta, P. , Maulik, U. 2007. Binary object extraction using bi-directional self-organizing neural network (BDSONN) architecture with fuzzy context sensitive thresholding Springer-Verlag London Limited
  21. Ghosh, A. and Sen, A. "Self organizing neural network for multi-level image segmentation," Soft Computing Applications to Pattern Recognition
  22. Ghosh, A. , Pal, N. R. , Pal, S. K. 1993 Self-organization for object extraction using multilayer neural network and fuzziness measures. IEEE Trans Fuzzy Syst 1(1):54–68
  23. Bhattacharya, S. , Pal, P. , Bhowmick, S. - A Quantum Multilayer Self Organizing Neural Network (QMLSONN) For Binary Object Extraction From A Noisy Perspective.
  24. Ross, T. J. , Ross, T. 1995 Fuzzy logic with engineering applications. McGraw Hill CollegeDiv.
  25. Bhattacharyya S. , Dutta P. , Maulik U. 2006 A self-supervised bi-directional neural network (BDSONN) architecture for object extraction guided by beta activation function and adaptive fuzzy context sensitive thresholding. Int J Intell Technol 1(4):345–365.
Index Terms

Computer Science
Information Sciences

Keywords

Binary object extraction Fuzzy context sensitive thresholding Quantum computing Multilayer self-organizing neural network Quantum back-propagation algorithm Bidirectional self-organizing neural network System transfer index Quantum multilayer self-organizing neural network.