Metal Label Pressed Protuberant Characters Segmentation Based on Shape Index

Wei Chen

doi:10.4028/www.scientific.net/AMR.187.672

Paper Titles

Analysis of Informatization Construction for SMEs with SaaS Model
p.652

Modeling Fiber Point Diffraction with Vector Theory for FPDI Design
p.658

The Appraisal Model on the Competitiveness of City Exhibition Industry
p.663

Metal Label Pressed Protuberant Characters Recognition Based on Hidden Markov Model
p.667

Metal Label Pressed Protuberant Characters Segmentation Based on Shape Index
p.672

Microscopic Traffic Simulation Based Dispatch Modeling for Taxi Booking Service
p.677

Research and Implementation of Image Fusion Algorithm Based on Wavelet Transform
p.683

Modifying Wind Speed Data of Manual Observation Sequence to Automatic Observation Sequence Using a PSO-Based Neural Network
p.688

Improving Image Contrast of Fiber Point Diffraction Interferometer
p.693

HomeAdvanced Materials ResearchAdvanced Materials Research Vol. 187Metal Label Pressed Protuberant Characters...

Metal Label Pressed Protuberant Characters Segmentation Based on Shape Index

Abstract:

According to metal label image characteristic, the pressed protuberant characters segmentation method is proposed based on shape index. The pressed protuberant characters and the print character image is withdraws with the morphology processing. obtains the surface gradient is gathered through the shape from shading method, then obtains the shape index operator, and realizes the classification by this as the feature vector through the support vector machines method. Compares with the classics image segmentation algorithm, this algorithm has the very big serviceability when grayscale image distribute is non-uniform. This method algorithm is simple, the effect is fine, not label layout restraint.

You might also be interested in these eBooks

Sport Materials, Modelling and Simulation

View Preview

Info:

Periodical:

Advanced Materials Research (Volume 187)

Pages:

672-676

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.187.672

Citation:

Cite this paper

Online since:

February 2011

Authors:

Wei Chen

Keywords:

Character Segmentation, Pressed Protuberant Character, Shape from Shading, Shape Index, Support Vector Machine (SVM)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Song Huaibo, Lu Changhou and Li Guoping: The Recognition of Laser Etched Characters Based on Three Cross Point, Journal of Optoelectronics Laser, vol. 18(2007), pp.1465-1469.

Google Scholar

[2] LU Changhou, CAO Janhai and LI Xueyong: Product quality on-line testing for the pressed protuberant character on a metal tag, Chinese Journal of Mechanical Engineering, (2005), pp.87-91.

DOI: 10.3901/jme.2005.02.087

Google Scholar

[3] R. zhang，P. -s．Tsai，J．ECfyer and M．Shall: shape from Shading：A survey, IEEE Trans. on Pattern Amlysis and Machine Intelligence(PAMI'21(8), (1999), pp.690-705.

Google Scholar

[4] A. Bab-Hadiashar and N. Gheissari: Range image segmentation using surface selection criterion, IEEE Trans. on Image Processing, vol. 15, no. 7, (2006).

DOI: 10.1109/tip.2006.877064

Google Scholar

[5] A. Gray,E. Abbena, and S. Salamon: Modern Differential Geometry of Curves and Surfaces with Mathematica 3rd, CRC press, p.342-p.377, NY (2006).

Google Scholar

[6] E. Prados, O. Faugeras, Perspective shape from shading and viscosity solutions, in: Proceedings of the Ninth IEEE International Conference on Computer Vision (vol. II), Nice, France, ( 2003) p.826–831.

DOI: 10.1109/iccv.2003.1238433

Google Scholar

[7] A. Tankus, N. Sochen, Y. Yeshurun, A new perspective on shape from-shading, in: Proceedings of the Ninth IEEE International Conference on Computer Vision (vol. II), Nice, France, (2003), p.862–869.

DOI: 10.1109/iccv.2003.1238439

Google Scholar