Solar cells defect detection in electroluminescence images

The defect will be introduced inevitably during the complexity manufacturing process of the solar cell. The existence of the defect significantly affects generating efficiency and service life. In this paper, the electroluminescence imaging technology is applied to highlight the defect. Aiming at the low rate of artificial detection and deficiency of objectivity, the algorithm of detecting defect which is based on statistics is proposed. In detection, the extensional Haar features are selected as the feature values of the pixel points. The improved fuzzy C-means clustering method is used to cluster the normal samples. By judging whether the testing sample is in the cluster of normal samples, the defect detection is carried out, and the location of the defect is provide at the same time. Experimental result shows that the total recognition rate of the defect in the electroluminescence image of solar cell is 96%.