Handwritten Character Recognition Using Multiscale Neural Network Training Technique
Advancement in Artificial Intelligence has lead to the
developments of various “smart" devices. Character recognition
device is one of such smart devices that acquire partial human
intelligence with the ability to capture and recognize various
characters in different languages. Firstly multiscale neural training
with modifications in the input training vectors is adopted in this
paper to acquire its advantage in training higher resolution character
images. Secondly selective thresholding using minimum distance
technique is proposed to be used to increase the level of accuracy of
character recognition. A simulator program (a GUI) is designed in
such a way that the characters can be located on any spot on the
blank paper in which the characters are written. The results show that
such methods with moderate level of training epochs can produce
accuracies of at least 85% and more for handwritten upper case
English characters and numerals.
[1] Wu, P.H. (2003), Handwritten Character Recognition, B.Eng (Hons)
Thesis, the School of Information Technology and Electrical
Engineering, the University of Queensland.
[2] Liou, C.Y. & Yang, H.C. (1996), "Hand printed Character Recognition
Based on Spatial Topology Distance Measurement", IEEE Transactions
On Pattern Analysis and Machine Intelligence, Vol. 18. No. 9, pp 941-
945.
[3] Didaci, L. & Giacinto, G. (2004), Dynamic Classifier Selection by
Adaptive k-Nearest-Neighbourhood Rule, Available:
http://ce.diee.unica.it/en/publications/papers-prag/MCS-Conference-
19.pdf (Accessed: 2007, October 11th).
[4] Brown, E.W. (1993), Applying Neural Networks to Character
Recognition, Available:
http://www.ccs.neu.edu/home/feneric/charrecnn.html (Accessed: 2007,
October 11th).
[5] Robinson, G. (1995), The Multiscale Technique, Available:
http://www.netlib.org/utk/lsi/pcwLSI/text/node123.html (Accessed:
2007, October 11th).
[6] Handwritten Character Recognition, Available:
http://tcts.fpms.ac.be/rdf/hcrinuk.htm (Accessed: 2007, October 11th).
[7] Rivals I. & Personnaz L. A statistical procedure for determining the
optimal number of hidden neurons of a neural model. Second
International Symposium on Neural Computation (NC.2000), Berlin,
May 23-26 2000.
[1] Wu, P.H. (2003), Handwritten Character Recognition, B.Eng (Hons)
Thesis, the School of Information Technology and Electrical
Engineering, the University of Queensland.
[2] Liou, C.Y. & Yang, H.C. (1996), "Hand printed Character Recognition
Based on Spatial Topology Distance Measurement", IEEE Transactions
On Pattern Analysis and Machine Intelligence, Vol. 18. No. 9, pp 941-
945.
[3] Didaci, L. & Giacinto, G. (2004), Dynamic Classifier Selection by
Adaptive k-Nearest-Neighbourhood Rule, Available:
http://ce.diee.unica.it/en/publications/papers-prag/MCS-Conference-
19.pdf (Accessed: 2007, October 11th).
[4] Brown, E.W. (1993), Applying Neural Networks to Character
Recognition, Available:
http://www.ccs.neu.edu/home/feneric/charrecnn.html (Accessed: 2007,
October 11th).
[5] Robinson, G. (1995), The Multiscale Technique, Available:
http://www.netlib.org/utk/lsi/pcwLSI/text/node123.html (Accessed:
2007, October 11th).
[6] Handwritten Character Recognition, Available:
http://tcts.fpms.ac.be/rdf/hcrinuk.htm (Accessed: 2007, October 11th).
[7] Rivals I. & Personnaz L. A statistical procedure for determining the
optimal number of hidden neurons of a neural model. Second
International Symposium on Neural Computation (NC.2000), Berlin,
May 23-26 2000.
@article{"International Journal of Information, Control and Computer Sciences:51164", author = "Velappa Ganapathy and Kok Leong Liew", title = "Handwritten Character Recognition Using Multiscale Neural Network Training Technique", abstract = "Advancement in Artificial Intelligence has lead to the
developments of various “smart" devices. Character recognition
device is one of such smart devices that acquire partial human
intelligence with the ability to capture and recognize various
characters in different languages. Firstly multiscale neural training
with modifications in the input training vectors is adopted in this
paper to acquire its advantage in training higher resolution character
images. Secondly selective thresholding using minimum distance
technique is proposed to be used to increase the level of accuracy of
character recognition. A simulator program (a GUI) is designed in
such a way that the characters can be located on any spot on the
blank paper in which the characters are written. The results show that
such methods with moderate level of training epochs can produce
accuracies of at least 85% and more for handwritten upper case
English characters and numerals.", keywords = "Character recognition, multiscale, backpropagation,
neural network, minimum distance technique.", volume = "2", number = "3", pages = "679-6", }