Application of Improved Moment Invariants and SVM in the Recognition of Solar Cell Debris

Yong Qing Wang; Dan Tian; Deng Yuan Song; Ai Ling Cai; Yu Fei Liu; Shi Yu Huang

doi:10.4028/www.scientific.net/AMR.805-806.21

Paper Titles

Efficiency Organic/Inorganic Composite Thin Film Solar Cells
p.3

Study on Solar Photovoltaic Industry Chain Vertical Integration Investment Decisions
p.7

Economic Analysis of Solar Trough, Tower and Dish Power Plants
p.12

Thermal Character and Generating Capacity Analysis of Solar Linear Fresnel Thermal Power Plant
p.17

Application of Improved Moment Invariants and SVM in the Recognition of Solar Cell Debris
p.21

Research on Testing Method of PV Inverter Flicker Based on IEC Standards
p.27

EMI Noise Testing and Diagnosis for PV Inverter
p.31

Substrate with Si Nanoparticles Prepared by Low Pressure Chemical Vapor Deposition for Application in Si Solar Cells
p.36

Test Analysis on the Electromagnetic Environment of Photovoltaic Power Transmission System
p.40

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 805-806Application of Improved Moment Invariants and SVM...

Application of Improved Moment Invariants and SVM in the Recognition of Solar Cell Debris

Abstract:

Automatic identification of defects on solar cell modules is the key of improving components efficiency of power generation and achieving the maximum utilization of energy[1]. This paper took the debris defects as an example. Considered the fact that scale factor would have an impact on moment invariants in discrete state, this paper adopted an improved moment invariant for the image feature extraction of debris defects. The scale factor of the new moment invariants is eliminated by transformation. Therefore they have the properties of translation, rotation and scaling simultaneously. Meanwhile, SVM (Support Vector Machine) classifier was used to identify the debris defects. The experimental results show that, compared with the traditional moment invariants, the identification rate of using the improved moment invariants for feature extraction is 96%.

You might also be interested in these eBooks

Solar Cells: Research and Development of Solar Cells

View Preview

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 805-806)

Pages:

21-26

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.805-806.21

Citation:

Cite this paper

Online since:

September 2013

Authors:

Yong Qing Wang*, Dan Tian, Deng Yuan Song, Ai Ling Cai, Yu Fei Liu, Shi Yu Huang

Keywords:

Feature Extraction, Moment Invariants, Solar Energy, Support Vector Machine (SVM)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Du Ming, LI Wei-Chen: Solar energy materials and solar cells(In Chinese), 2012, 11(9): 250-262.

Google Scholar

[2] Milan Sonka Vaclav Hlavac Roger Boyle: Vision of image processing, analysis, and machine [M]. Beijing: Tsinghua University press, 2011. 95.

DOI: 10.1117/12.256634

Google Scholar

[3] DavidA, Forsyth Jean Ponce: Computer vision [M]. Beijing: Tsinghua University press, (2004).

Google Scholar

[4] Jovisa Zunic, Kaoru Hirota , Paul L. Rosin: Pattern Recognition, 2013, 43(1), 47-57.

Google Scholar

[5] Yajuan Lin. The moment invariants theory of automatic recognition technology [D](In Chinese). Xi'an: Northwestern Polytechnical University, (2000).

Google Scholar

[6] Lijuan Guo, Shiyu Sun, Xiusheng Duan. Science technology and engineering(In Chinese), 2008, 21 (2): 487 – 490.

Google Scholar

[7] Lv Zhe, Wang Fuli, Chang Yuqing: Journal of Northeastern University(In Chinese), 2007, 28 (12): 1681-1684.

Google Scholar

[8] Xiaohui Liu, Xu Lin, Xiao Chenjiang: Journal of Shanghai Jiao Tong University(In Chinese), 2010, 44 (7): 926-930.

Google Scholar