Application of Improved Invariant Moments and SVM in the Recognition of Solar Cell Defects

Abstract:

The infrared image of solar cell's electroluminescence (EL) is one of the important means of hidden defects detection. In order to improve the automatic recognition rate of defect images, this paper adopts improved invariant moments for feature extraction. The scale factor of the improved invariant moments is eliminated by transformation. Therefore they have the properties of translation, rotation and scale invariance simultaneously in discrete state. At the same time, Support Vector Machine (SVM) is used to distinguish the defect image. The system which combined invariant moments with SVM is applied to classify the debris, crack, off-grid, open weld and black pieces. The recognition rate of 5 kinds of defects has reached more than 90%.

• Periodical: Applied Mechanics and Materials (Volumes 672-674)
• Pages: 3-6
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.672-674.3
• Online since: October 2014
• Authors: Yong Qing Wang, Dan Tian*, Deng Yuan Song, Lei Zhang
• Keywords: Electroluminescence (EL), Feature Extraction, Infrared Image, Invariant Moments, Solar Cell Defect, Support Vector Machine (SVM)

References

[1] Qiu Shengyu, Li Yangsheng. Morphology and formation mechanism of liner defects on solar-energy multicrystalline silicon wafers[J]. Acta energiae solaris sinica, 2012, 33(5): 802-805.

[2] Wang Chao, Jiang Xiaoyu, Liu Xiaohui. Defect detection in crystalline silicon solar cells based on electroluminescence imaging[J]. Journal of Optoelectronics·Laser, 2011, 22(9): 1332-1336.

[3] Jovisa Zunic, Kaoru Hirota, Paul L. Rosin. A Hu moment invariant as a shape circularity measure[J]. Pattern Recognition, 2013, 43(1): 47-57.

DOI: 10.1016/j.patcog.2009.06.017

[4] Sun Junding, Wu Xiaosheng. Image retrieval based on entropy and invariant moments[J]. Opto-Electronic Engineering, 2007, 34(6): 102-106+115.