Hand Written English Character Recognition using Pattern Sampling Recognition Technique (PSRT)
DOI:
https://doi.org/10.26438/ijcse/v6i10.5861Keywords:
Character recognition, Sampling, Perceptron, Learning Algorithm, Neural NetworkAbstract
This is the era of intelligent computing devices. Efforts are going on in all over the world to develop machines and programs which can solve the problems that human beings can solve with ease. One such field is recognition of handwritten characters by computers. In this paper the neural network is first trained using perceptron-learning algorithm. The target pattern is a collection of distinct patterns set for each character. While testing the target pattern is sampled and the distortion in the sampled pattern was compared with the original one. 30% or less of such distortion was considered for the identification of a particular character. The results showed that such methods produce accuracies of at least 90% and more for the hand written upper case English alphabets
References
[1] L van der Maaten-2009, A New Benchmark Data Set for Handwritten Character Recognition, Available: www.tilburguniversity.nl/faculties/humanities/ticc/.../TR2009002.pdf, (Accessed: 2010, July 19th)
[2] Brown, E.W. (1993), Applying Neural Networks to Character Recognition, Available: http://www.ccs.neu.edu/home/feneric/charrecnn.html (Accessed: 2010, July 19th).
[3] Robinson, G. (1995), The Multiscale Technique, Available: http://www.netlib.org/utk/Isi/pcwLSI/text/node123.html
[4] Handwritten Character Recognition, Available: http://tcts.fpms.ac.be/rdf/hcrinuk.htm
[5] Velappa Ganapathy, and kok Leong Liew, Handwritten Character Recognition Using Multiscale Neural Network Training Technique, World Academy of Science, Engineering and Technology 39 2008
[6] Sandhya Arora, Debotosh Bhattacharjee, Mita Nasipuri, Dipak kumar Basu and Mahantapas Kundu, Combining Multiple Feature Extraction Techniques for Handwritten Devnagri Character Recognition, Available: http://arxiv.org/ftp/arxiv/papers/1005/1005.4032.pdf, (Accessed: 26, July, 2010).
[7] Dayashankar Singh, Sanjay Kr. Singh and Dr. (Mrs.) Maitreyee Dutta, Hand Written Character Recognition Using Twelve Directional Feature Input and Neural Network, Available: http://www.ijcaonline.org/journal/number3/pxc387173.pdf, (Accessed: 26, July, 2010).
[8] Fu Chang, Chin-Chin Lin and Chun-Jen Chen, Applying A Hybrid Method To Handwritten Character Recognition, www.iis.sinica.edu.tw/~fchang/paper/931_chang_F.pdf, (Accessed: 26, July, 2010).
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
