Free Handwritten Numeral Recognition Based on BP Neural Network

Miao Chao Chen; Fang Wang

doi:10.4028/www.scientific.net/AMR.850-851.909

Paper Titles

Heuristic Dynamic Programming Iterative Algorithm Design Based on BP Neural Network
p.893

The Improved Method for Image Edge Detection Based on Wavelet Transform with Modulus Maxima
p.897

Hopf Bifurcation and Stability Analysis for a Predator-Prey Model with Delays
p.901

An Express Retrieval Method of Face Based on Semantic Features
p.905

Free Handwritten Numeral Recognition Based on BP Neural Network
p.909

A Modified Algorithm Based on Decoration VSSLMS
p.913

An Improved Motion Compensation Algorithm Based on Discriminant Analysis
p.918

The Passive Target Motion Parameters Estimate Algorithm Based on Particle Filter
p.922

Sensitivity Analysis to Attribute Values Based on Grey Correlation in Multiple Attribute Decision Making
p.927

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 850-851Free Handwritten Numeral Recognition Based on BP...

Free Handwritten Numeral Recognition Based on BP Neural Network

Abstract:

Handwritten numeral recognition is an important branch in the field of pattern recognition, has broad application prospects. This article presents a method of using BP Neural Network to implement programme for recognition of free handwritten numerals. Scanned handwritten numeral image after preprocessing and feature extraction, classificated and recognized by the BP Neural Network. Through Matlab simulation experiments it shows that the recognition method is effective and has high recognition rate.

You might also be interested in these eBooks

Advances in Applied Sciences and Manufacturing

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 850-851)

Pages:

909-912

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.850-851.909

Citation:

Cite this paper

Online since:

December 2013

Authors:

Miao Chao Chen*, Fang Wang

Keywords:

BP Neural Network (BPNN), Handwritten Numeral Recognition, Target Value

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] D. M, A. H. Plurality voting-based multiple classifier systems: statistically independent with respect to dependent classifier sets. Pattern Recognition. Vol. 35(2002), pp.2365-2379.

DOI: 10.1016/s0031-3203(01)00227-8

Google Scholar

[2] X. X, F.L. QSPR models for the prediction of odor threshold of aliphatic alcohols. Journal of Computational Science & Engineering. Vol. 2(2011), pp.69-78.

Google Scholar

[3] B.J. C: Pattern recognition with fuzzy objective function algorithms: Kluwer Academic Publishers. (1981).

Google Scholar

[4] J.Z.L. Artificial Neural Networks. Beijing : Higher Education Press. (2001).

Google Scholar

[5] D. D, L.H.D. Pattern Classification. The Machinery Industry Press. (2003).

Google Scholar

[6] H.D. Feature extraction for handwritten digit recognition and study on feature selection. Beijing: Posts and Telecommunications. (2007).

Google Scholar

[7] M. Y, H.M. Digit recognition based on BP Neural Network. Information technology, Vol. 4 (2007), pp.87-88.

Google Scholar

[8] Peilong Xu. Study on Moving Objects by Video Monitoring System of Recognition and Tracing Scheme, TELKOMNIKA, Vol. 11, No. 9, September 2013, p.4847~4853.

DOI: 10.11591/telkomnika.v11i9.2740

Google Scholar