Comparative Study of Algorithms to Recognise Handwritten Digits

Article Sidebar

PDF
Published: May 31, 2021
Keywords:
Back propagation Network, MNIST data set, TensorFlow, Logistic Regression Algorithm, Matlab, Accuracy, Confusion Matrix

Main Article Content

Anushka Sharma
Prateek Dhawan
SwarnalathaP

Abstract

The paper shows how different estimations can be applied to test the exactness of the neural associations. We separate the display of the Back spread estimation with changing getting ready plans and the ensuing power term in feed-forward neural associations. In a relationship, we analyze the essential backslide estimation, which makes a choice based on the value of an immediate blend of the features. In this paper, Neural Associations are used with an MNIST dataset of 70000 digits and 250 assorted creating styles. Logistic Regression is a measurable model that, in its fundamental structure, utilizes a strategic capacity to demonstrate a twofold reliant variable, albeit a lot more intricate expansions exist. In relapse examination, calculated relapse (or logit relapse) assesses the boundaries of a strategic model (a type of paired relapse). This equivalent examination shows the exactness of these computations in distinguishing physically composed digits, with Backpropagation unequivocally expecting close 95.06% of the test dataset when it was run multiple times, and the essential logistic regression correctly anticipating close 99% with a hidden layer and 92% without a hidden layer.

Article Details

How to Cite
[1]
Anushka Sharma, Prateek Dhawan, and SwarnalathaP, “Comparative Study of Algorithms to Recognise Handwritten Digits”, Int. J. Comput. Eng. Res. Trends, vol. 8, no. 5, pp. 95–101, May 2021.
Issue
Vol. 8 No. 5 (2021): May (2021) Issue
Section
Research Articles
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

IJCERT Policy:

The published work presented in this paper is licensed under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. This means that the content of this paper can be shared, copied, and redistributed in any medium or format, as long as the original author is properly attributed. Additionally, any derivative works based on this paper must also be licensed under the same terms. This licensing agreement allows for broad dissemination and use of the work while maintaining the author's rights and recognition.

By submitting this paper to IJCERT, the author(s) agree to these licensing terms and confirm that the work is original and does not infringe on any third-party copyright or intellectual property rights.

 

References

S. Mori, C.Y. Suen and K. Kamamoto, “Historical review of OCR research and development,†Proc. of IEEE, vol. 80, pp. 1029-1058, July 1992.

S. Impedovo, L. Ottaviano and S. Occhinegro, “Optical character recognitionâ€, International Journal Pattern Recognition and Artificial Intelligence, Vol. 5(1-2), pp. 1-24, 1991.

V.K. Govindan and A.P. Shivaprasad, “Character Recognition – A review,†Pattern Recognition, vol. 23, no. 7, pp. 671- 683, 1990 International Journal of Computer Science & Information Technology (IJCSIT), Vol 3, No 1, Feb 2011 37

R. Plamondon and S. N. Srihari, “On-line and off- line handwritten character recognition: A comprehensive survey,â€IEEE. Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 1, pp. 63-84, 2000.

N. Arica and F. Yarman-Vural, “An Overview of Character Recognition Focused onOff-line Handwritingâ€, IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, 2001, 31(2), pp. 216 - 233.

U. Bhattacharya, and B. B. Chaudhuri, “Handwritten numeral databases of Indian scripts and multistage recognition of mixed numerals,†IEEE Transaction on Pattern analysis and machine intelligence, vol.31, No.3, pp.444-457, 2009.

U. Pal, T. Wakabayashi and F. Kimura, “Handwritten numeral recognition of six popular scripts,†Ninth International conference on Document Analysis and Recognition ICDAR 07, Vol.2, pp.749-753, 2007.

R.G. Casey and E.Lecollinet, “A Survey of Methods and Strategies in Character Segmentation,†IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 18, No.7, July 1996, pp. 690-706.

Anil.K.Jain and Torfinn Taxt, “Feature extraction methods for character recognition-A Survey,†Pattern Recognition, vol. 29, no. 4, pp. 641-662, 1996