Building Data Mining Classification Model For Pixilated Digit Recognition System

International Journal of Computer Science and Engineering

© 2020 by SSRG - IJCSE Journal

Volume 7 Issue 10

Year of Publication : 2020

Authors : Ziweritin, Stanley, Ukegbu, C. C, Ezeorah, E. U

10.14445/23488387/IJCSE-V7I10P102

How to Cite?

Ziweritin, Stanley, Ukegbu, C. C, Ezeorah, E. U, "Building Data Mining Classification Model For Pixilated Digit Recognition System," SSRG International Journal of Computer Science and Engineering , vol. 7,  no. 10, pp. 6-12, 2020. Crossref, https://doi.org/10.14445/23488387/IJCSE-V7I10P102

Abstract:

Recognition is one of the major areas that have attracted the attention of different researchers, which can be applied in every sphere of life as technology advances. There are several problem domains in adopting data mining classification models with the rise in an exponential growth of structured and unstructured data. High metrics of success rate has not been recorded despite the existence and usefulness of data mining classification models in practice. Especially in the areas of testing and training of classifiers to recognize digits on pixilated images like the existing methods which are not efficient and encouraging in terms of speed and accuracy. Because of the segmented colour grid arrangements or formation of some digits. Therefore; we adopted the proposed model to overcome the challenges facing the methods on pixilated digit recognition systems. The aim is to build an efficient pixilated digit recognition system using neural network and support vector machine data mining classification models which can recognize digits within the range of 0-to-9 inclusively from pixilated or raster images. The system was successfully trained and tested in comparison to ascertain 94% and 99% accuracy level for support vector machine and neural network models respectively using Python programming language.

Keywords:

Neural network, data mining, support vector machine, pixilated digit, recognition

References:

[1] M. J. Aditi, and T. kinjal, "A Survey on Digit Recognition using Deep Learning", International Journal of Novel Research and Development(IJNRD), ISSN: 2456-4184 Vol. 3 issue 4, April 2018, pp. 112-118
[2] P. Ayush, and S. S. Chauhan, "A Literature Survey on Handwritten Character Recognition", International Journal of Comp. Science and Information Technologies, Vol. 7 Issue 1, January - February 2016. pp. 1-5.
[3] V. Chandola, A. Banerjee, and V. Kumar, "Anomaly detection: a survey," ACM Computing Surveys (CSUR), Vol. 41 issues 3, pp. 15, 2009
[4] C. C. Dan, U. Meier, L. M. Gambardella, and J. Schmidhuber, (2010) "Deep big simple neural Nets Excel On Handwritten Digit Recognition", MIT Press, 56-876.
[5] L. Deng, "The MNIST Database of Handwritten Digits images for Machine Learning Research", MIT Press, pp. 46-876, 2012
[6] B. Hyeran, and L. Seong-whan, "A survey on pattern recognition applications of support vector machines", International Journal of Pattern Recognition and Artificial Intelligence (AI) Vol. 17, issue 3, pp. 459–486, 2003
[7] S. Karen, and Z. Andrew, "Very deep convolutional networks for large-scale image recognition", arXiv preprint arXiv: 1409.1556, 2014.
[8] H. Kaur, S. K. Wasan, "Empirical study on applications of data mining techniques in healthcare". Journal of Computer Science(JCS). Vol. 2, issue 2, pp. 194–200, 2006
[9] I. J. Kim, and X. Xie, "Handwritten Hangul recognition using deep convolutional neural networks". International Journal on Document Analysis and Recognition (IJDAR), Vol. 18, issue 1, pp. 1–13, 2014
[10] F. Lauer, C. Suen, and G. Bloch, "A trainable feature extractor for handwritten digit recognition", Pattern Recognition, Vol. 40, issue 6, pp.1816–1824, 2007
[11] G. Mamta, P. Muktsar, A. Deepika, and P. Muktsar, (2013), "A Novel Approach to Recognize the offline Handwritten Numerals using MLP and SVM Classifiers", International Journal of Computer Science & Engineering Technology (IJCSET), ISSN: 2229-3345,4(7), 952-958.
[12] Y. Perwej, and A. Chaturvedi, "Neural Networks for Handwritten English Alphabet Recognition". Journal of Natural Sciences and Engineering(JNSE), Vol. 2, pp.67-89, 2011
[13] E. Salvador, J. C. B., Maria, G. M. Jorge, and Z. M. Francisco, "Improving Offline Handwritten Text Recognition with Hybrid HMM/ANN Models", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 33, issue 4, pp.45-78, 2014
[14] P. Sarma, S. Sarmah, M. P. Bhuyan, K. Hore, and P. P. Das, "Automatic Spoken Digit Recognition Using Artificial Neural Network", International Journal of Science and Technology(IJST), Vol. 8, issue 12, ISBN 2277-8616, pp.1400-1404, 2019
[15] M. Shashank, D. Malathi, and K. Senthilkumar, "Digit Recognition using Deep Learning", International Journal of Pure and Applied Mathematics, ISSN: 1314-3395, Vol. 118, issue 22, pp. 95-301, 2018.
[16] C. Shengfeng, G. Yuwen, W. Lee, and A. Rabia, "Offline Handwritten Digits Recognition Using Machine learning", International Conference on Industrial Engineering and Operations Management Washington DC, USA, IEOM Society International, pp.275-286, 2018.
[17] A. A. Tsehay, and S. N. Pramod, "Hand-written Digits Recognition with Decision Tree Classification: a Machine Learning Approach", International Journal of Electrical and Computer Engineering (IJECE), Vol. 9, issue 5, ISSN: 2088-8708, DOI: 10.11591, pp.4446-4451, 2019
[18] S. Vinneet, and P. L. Sunil, "Digits recognition using single-layer neural Network with principal component analysis", Computer Science and Engineering (APWC on CSE), Asia-Pacific World Congress IEEE, 4-5, 2014.
[19] S. Zhang, C. Tjortjis, X. Zeng, H. Qiao, Buchan, I., Keane, J.: "Comparing data mining methods with logistic regression in childhood obesity prediction". Inf. Syst. Front, Vol. 11, issue 4, pp.449–460, 2009.