Volume : 2, Issue : 7, JUL 2016
CHARACTER RECOGNITION BY ARTIFICIAL NEURAL NETWORK METHODS
Abdulrahim M. Ahmad, Sahar Mahdie Klim, Maab Alaa Hussain
Within the domain of computer science, numerous objectives arise. Automatic processing of data is imperative in many fields and for this purpose a number of techniques are implemented; one of which is Artificial Neural Network. Artificial intelligence is concerned with building an intelligent machine, whereas artificial neural network is after creating a learning system which is based on little and simple framework program capable of responding to problem and getting feedback on how it does so. Based on the human brain principle, the artificial neural network is built in such a way that makes it capable of learning things that will enable it later to solve problems according to the bases information it has learned. It is also capable of solving adaptive problems due to its ability to conduct adaptive learning. The current paper study several properties where the human nervous system and the artificial neural network are compared. Also an application for the recognition of scanned handwritten characters by artificial neural network is employed.
Neural Network, Artificial Neural Network, Back propagation, Bayesian Artificial Neural Network.
Article : Download PDF
Cite This Article
Article No : 20
Number of Downloads : 372
1. M. Hajek, " Neural Networks ", thesis, 2005.
2. R.Rojas, " Neural Networks A systematic Introduction", Springer-Verlag, Berlin, 1996.
3. Panduranga, P.P. ; KLS Gogte Inst. of Technol., Belgaum, Rao, D.H. Deshpande,
A.Fault “Tolerance Analysis of Neural Networks for Pattern Recognition”2000.
4. S. Kullback, " Information Theory and Statistics", Dover, 1968.
5. AL-Dulaimi, Buthaina ;Ali, Hamza, "Enhanced Traveling Salesman Problem Solving
by Genetic Algorithm Technique (TSPGA)",world Academy of Science, Engineering
and Technology ,Page 296.(2008).
6. p. Forsland, " A neural Network Based Brain – computer Interface for Classification of
Movement Related EEG", Thesis, Linkoping, December, 2003.
7. R.Gencay and M. Qi, " Princing and Heading Derivative Securities with Neural Networks:
Bayesian Regularization, Early stopping, and Bagging", IEEE Transaction on
Neural Network , Vol.12, No. 4, July, 2001.
8. D. Graupe, " PRINCIPLES OF ARTIFICIAL NEURAL NETWORKS ", 2nd Edition,
ADVANCED SERIES IN CIRCUITS AND SYSTEMS, Vol. 6, University of lllinois,
9. S.Hiregoundar, Manjunath.K, K. S. Patil, " A survey: Research Summary on Neural
Network ", IJRET: International Journal of Research in Engineering and Technology,
Vol.03, Issue 03, May, 2014.
10. U. N. Lerner, "Hybrid Bayesian Networks for Reasoning about Complex Systems",
Computer science department, Stanford University, 2002.
11. P. W. Kasteleyn, "Dimer Statistics and Phase Transitions", Journal of Mathematical
12. V K Jian, New Delhi 2009 , "Information Technology issue and challenges", ISBN:
13. Y. L. Loh, E. W. Carlson, and M. Y. J. Tan, "Bond-propagation algorithm for thermodynamic
functions ingeneral two-dimensional Ising models", Physical Review B,
14. G. Kitagawa, "The Two-Filter Formula for Smoothing and an implementation of the
Gaussian-sum smoother", Annals of the Institute of Statistical Mathematics,
15. AL- Naima F, Al-Timemy A, “Resileint Back Propagation Algorithm for Breast
Biospy Classification Based on Artificial Neural Network”, (2010), Computational
Intelligence and Modern Heuristics.
16. M. Dharlingam and R. Amalraj, " ARTIFICIAL NEURAL NETWORK ARCHITECTURE
FOR SOLVING THE DOUBLE DUMMY BRIDGE PROBLEM IN CONTRACT
BRIDGE", International Journal of Advanced Research in Computer and Communication
Engineering, Vol. 2, Issue 12, December 2013.
17. Gonzalez, R. C. et al., "Digital Image Processing", second edition. (addison- wesly
problishing company, Inc.), 1987.
18. C-J. Kim and C. R. Nelson, "State-Space models with regime switching", MIT Press,
19. D. Barber, " Bayesian Reasoning and Machine Learning", 2010.
20. Raudys, Sarunas, 2001 Statistical and Neural Classifiers "an integrated approach to
design",(Text Categorization by Back-propagation Network (0975 – 8887), 2010).
21. Halim Sh., Ahmed A., Noh N., Safudin M., and Ahmed R. “A comparative study
between Standard Back Propagation and Resilient Propagation on Snake Identification
Accuracy”. IEEE, Malaysia, 2011.