One small step for a man
One Giant leap for the mankind

There is no wealth like Knowledge
                            No Poverty like Ignorance
Journal of Emerging Trends in Computing and Information Sciences Logo

Journal of Emerging Trends in Computing and Information Sciences >> Call for Papers Vol. 8 No. 3, March 2017

Journal of Emerging Trends in Computing and Information Sciences

An Artificial Neural Network Model for Tiv Character Recognition (ANNTCR)

Full Text Pdf Pdf
Author Iorundu Gabriel Shimasaan, Esiefarienrhe Michael Bukohwo
ISSN 2079-8407
On Pages 573-583
Volume No. 6
Issue No. 10
Issue Date November 1, 2015
Publishing Date November 1, 2015
Keywords Tiv character recognition, resilient propagation algorithm, artificial neural network, feed forward neural network.


There has been growing need to put the Tiv language in the forefront of Information and Communication Technology (ICT) development by making the computer recognize the Tiv Character Set, develop Compilers to translate the Tiv language and subsequently, develop a programming language in Tiv. These are feasible possibilities that are not beyond the knowledge based of the Tiv people and their research partners. Therefore, the work seeks to use Artificial Neural Network (ANN) model to exploit the field of pattern recognition with specific application to the Tiv character recognition and modeling. In doing so, Macromedia Fireworks 8 was used in the preprocessing of the character images so as to reduce noise and jitter in the original character images. The pixel values of the characters were extracted with the aid of a self-written program in Java and normalized as a single vector which served as input data for the network training and testing. The Artificial Neural Network Model for Tiv Character Recognition (ANNTCR) was implemented using Java programming language which was based on Encog Framework. The design of the system was implemented using Resilient Propagation algorithm. Two hundred and fifty (250) samples of printed Tiv characters of different font types namely Aharoni, Arial, Courier, Franklin Gothic Heavy and Times New Roman were collected. Out of the collected samples, one hundred and seventy (170) samples were used as training data (training set) while the remaining eighty (80) samples were used as a test data (test set). The result shows that the average recognition rate of the system was 99.4% while the system’s rejection rate was below 1%. With this result, the Tiv language has been opened up for complete automation and subsequent compiler development.

    Journal of Computing | Call for Papers (CFP) | Journal Blog | Journal of Systems and Software | ARPN Journal of Science and Technology | International Journal of Health and Medical Sciences | International Journal of Economics, Finance and Management     
© 2015 Journal of Computing