The Research on Computer Recognition Technology for Blurred Alphabet Images

Chun Rong Liu

doi:10.4028/www.scientific.net/AMM.644-650.4125

Paper Titles

Optimization of Quantum Dot Infrared Photodetectors Based on Noise Model
p.4107

Comparison between Mean Filter and Median Filter Algorithm in Image Denoising Field
p.4112

Acquisition and Recovery of Full-Waveform LIDAR Data Based on Compressive Sensing
p.4117

Three-Dimensional Recognition Technology for Rare English Words
p.4121

The Research on Computer Recognition Technology for Blurred Alphabet Images
p.4125

Simulation Analysis for Collecting Model of Train Remote Communication Signal
p.4129

The Simulation Analysis of the Signals Collection Model for Railway Locomotive Remote Communication
p.4132

The Athletes’ Irrational Posture Recognition Based on Minimizing Image Sequences
p.4136

Research on the Feature Parameter Extraction of Wheat Seeds’ Bad Point Based on Image Processing
p.4140

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 644-650The Research on Computer Recognition Technology...

The Research on Computer Recognition Technology for Blurred Alphabet Images

Abstract:

This paper mainly studies the recognition issue of blurred alphabet images. If alphabets in an image is blurred, it is difficult t be recognized. To avoid the defect, the paper proposes a computer recognition method for blurred alphabet images based on grayscale class variance algorithm. The algorithm executes non-linear transformation on feature parameters of alphabets images extracted to obtain eigenvector coefficient weights, and then calculates characteristic correlation coefficient through wavelet transform to realize the blurred alphabet recognition. Experiments show that, the proposed method improves the accuracy of the blurred alphabets recognition and achieves satisfactory results.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 644-650)

Pages:

4125-4128

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.644-650.4125

Citation:

Cite this paper

Online since:

September 2014

Authors:

Chun Rong Liu*

Keywords:

Alphabets Recognition, Blurred, Characteristic Correlation

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] yong-hua xu, wu min, wei-hua cao, etc. The blast furnace temperature field recognition of infrared image detection method and application [J]. Journal of control engineering, 2005, 12 (4) : 354-356.

Google Scholar

[2] fang-fang zhang, image stitching algorithm based on neighborhood gradient study [J]. BULLETIN OF SCIENCE AND TECHNOLOGY , 2012, 10 (28) : 61-63.

Google Scholar

[3] wenwu, yellow lumbricus, Guo Xirong. The application of prudential denoising in image preprocessing [J]. Infrared technology, 2006, 28 (7) : 415-418.

Google Scholar

[4] Jia Xiaojun, yu qing pale. Based on open source computer vision library OpenCV image processing [J]. Journal of computer applications and software, 2008. 4: 276-278.

Google Scholar

[5] w. b. Horng, j. w. Peng, c. y. Chen, A new image -based real - time flame detection method using color analysis [J], in the Conf ICNSC, 2005, IEEE, 2005: 100-105.

DOI: 10.1109/icnsc.2005.1461169

Google Scholar

[6] Ben - Ezra m. Segmentation with invisible keying signal [J]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2000, 1: 32 to 37.

DOI: 10.1109/cvpr.2000.855795

Google Scholar