Design and Realization of the SMT Product Character Recognition System

Hui Huang Zhao; De Jian Zhou; Zhao Hua Wu

doi:10.4028/www.scientific.net/AMR.139-141.1736

Paper Titles

A Compression Algorithm for Vibration Signal of Rotating Machinery Based on Partitioned Iterated Function Systems
p.1718

Study on Trajectory Planning and Control Method in Profile Cutting of Roadheader
p.1723

A Study on Gray Relational Analysis of Many Factor Weights in Tobacco Leaves Classification
p.1728

A Novel Distributed Multi Agent System Plan Algorithm
p.1732

Design and Realization of the SMT Product Character Recognition System
p.1736

The Expert System of Prediction of Stroke for Precision Straightening Based on Database
p.1740

Error Modeling and Compensation of Linear Motors Positioning Stage Based on RBF Network
p.1744

The Electro-Hydraulic Proportional Control and Simulation of the Radial Piston Pump Based on Proportional-Integral-Derivative Neural Network
p.1749

The Assemblability Evaluation of Automotive Glass Windshield Mold Based on Fuzzy Neural Network
p.1753

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 139-141Design and Realization of the SMT Product...

Design and Realization of the SMT Product Character Recognition System

Abstract:

We present an approach to recognizing characters in surface mount technology (SMT) product. An improved SMT product character recognition method is proposed which can obtain a good recognition rate. Some appropriate image processing algorithms, such as Gray processing, Low-pass Filter, Median Filter, and so on, are used to eliminate the noise. Then, Character image is obtained after character segmentation and character normalization. Finally, a three-layer back propagation (BP) neural network module is constructed. In order to improve the convergence rate of the network and avoid oscillation and divergence, the BP algorithm with momentum item is used. As a result, the SMT product character recognition system is developed. Experimental results indicate that the proposed character recognition can obtain satisfactory character-recognition rate and the recognition rate reached over by 98.6% when the hidden layer of BP neural network module has 20 nodes.

You might also be interested in these eBooks

Manufacturing Engineering and Automation I

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 139-141)

Pages:

1736-1739

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.139-141.1736

Citation:

Cite this paper

Online since:

October 2010

Authors:

Hui Huang Zhao, De Jian Zhou, Zhao Hua Wu

Keywords:

BP Neural Network (BPNN), Character Recognition, Image Processing, Pattern Recognition, Surface Mount Technology (SMT)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Pati Peeta Basa, Ramakrishnan A G: Institution of Electronics and Telecommunication Engineers. Vol. 22 (2005), pp.217-227.

Google Scholar

[2] R Sanjeev Kunte, R D Sudhaker: SAMUEL: Vol, 32(2007). pp.521-533.

Google Scholar

[3] Manjunath Aradhya V N, and Hemantha Kumar G: First International Conference on Emerging Trends in Engineering and Technology(Nagpur, Maharashtra, July 16-18, 2008), pp.1170-1174.

Google Scholar

[4] D.J. ZHOU,C.Y. HUANG and Z.H. WU: Computer Integrated Manufacturing Systems. Vol. 12 (2006), pp.1267-1272(In Chinese).

Google Scholar

[5] Z Q Cheng, Y Z Ma: Proceedings of the 2008 ISECS International Colloquium on Computing, Communication, Control, and Management(Washington, DC, USA, August 3-4, 2008), pp.140-145.

Google Scholar

[6] J Sutha and N Ramaraj: 19th IEEE International Conference on Tools with Artificial Intelligence(2007), pp.446-450.

Google Scholar